sequant-io/sequant

View on GitHub

AI coding agent orchestrator — resolve GitHub issues end-to-end with isolated git worktrees, quality gates, and an MCP server. Works with Claude Code or Aider.

Is sequant-io/sequant beginner-friendly?

In the last 30 days, sequant-io/sequant merged 75 of 83 pull requests from outside contributors, and its maintainers usually reply within 1 day. 5 beginner-friendly issues are open now.

Stars: 1
Forks: 1
Open beginner issues: 5
Indexed issues: 212
Avg merge: 11h 3m
Merged PRs (30d): 84

Dominant language: TypeScript
License: MIT
Last GitHub push: Oct 9, 2026
Latest indexed: Oct 9, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

How to contribute to sequant-io/sequant

Read the contributing guide first: it says how the maintainers want changes proposed, tested and reviewed.
Your contributions will be published under the project's MIT license.
Pick one of the 5 open beginner-friendly issues below and comment that you want to work on it before you start.

Beginner friendly Everything

Open All

Issues somebody may already be working on are listed last. List everything by date

gate(owner): release sequant 3.0.0 — `/release` major from `main` after the smoke and the pin; `next` first, `latest` on the owner's word
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 1/100

sequant-io/sequant#1657 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
gate(owner): pin the harness and matcha-maps to sequant 2.20.0 before 3.0 is published
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 1/100

sequant-io/sequant#1656 · 1 comment · Opened Nov 7, 2026

Maintainers usually reply within 1 day
smoke(simplify): first real use — one detached run of a `main` build on two notes-fixture smoke issues, after #S-01 to #S-07 merge; the owner reads the report
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 25/100

sequant-io/sequant#1655 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
gate(owner): hook precision — 50 pre-tool blocks from the frozen logs, stratified by rule, labelled true or false; counts per rule published, block text kept private
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 5/5 Over a week Newbie friendliness 25/100

sequant-io/sequant#1654 · 1 comment · Opened Nov 7, 2026

Maintainers usually reply within 1 day
investigation(qa): pre-register #1068's section leave-one-out for qa on fixture #34, with the cost estimated before any run — written in the research repo, hash and estimate posted on #1068
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 18/100

sequant-io/sequant#1653 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
feat(qa): Evidence that names an env file, a production CLI or a live URL is handed to a person — classified in code, listed in the qa prompt as "do not run", recorded per AC in the run log, printed with its command in the run summary
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 45/100

sequant-io/sequant#1652 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
feat(run): `--chain` and multi-issue runs print an "experimental" warning with their measured success rates — fixed, dated counts; the code stays
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 3/5 1-2 days Newbie friendliness 72/100

sequant-io/sequant#1651 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
docs(ready): the ready gate's docs drop the second-look claim — describe the qa → loop → qa mechanism and its policy, cite #1344 for what was measured
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

sequant-io/sequant#1650 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
chore(cli)!: remove `--stacked`, `--reflect` and `--full-qa` — flags, `run.fullQa`, the MCP `fullQa` parameter and `run-reflect.ts`; `--chain` keeps working
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 35/100

sequant-io/sequant#1648 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
chore(cli)!: remove the model ladder and effort escalation — modules, `--model-ladder` and `--escalate-effort` on run and ready, their settings and docs; old logs and settings still load
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sequant-io/sequant#1647 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
tracker: graph-2026-11-simplify — sequant 3.0 cut to the measured shape: D-1 removals, a halt on a repeated AC_NOT_MET, the ready gate's claim dropped, chain and multi-issue marked experimental, production-reaching Evidence handed to a person, the downstream pin, the release
Open
- Is something wrong?
graph-2026-11-simplify

Difficulty 5/5 Over a week Newbie friendliness 15/100

sequant-io/sequant#1645 · Opened Nov 7, 2026

Maintainers usually reply within 1 day
run: an outdated committed skill tree runs under a newer CLI with a one-line warning and no record
Open
- Is something wrong?
Difficulty 3/5 1-2 days Newbie friendliness 42/100

sequant-io/sequant#1642 · Opened Nov 3, 2026

Maintainers usually reply within 1 day
docs + run: phase agents look for production credentials wherever the repo's docs name them; document it, and offer a deny list
Open
- Is something wrong?
Difficulty 3/5 1-2 days Newbie friendliness 35/100

sequant-io/sequant#1641 · Opened Nov 3, 2026

Maintainers usually reply within 1 day
run: with no model configured, each phase inherits Claude Code's user-level `model` and the run header says nothing about it
Open
- Is something wrong?
Difficulty 3/5 1-2 days Newbie friendliness 42/100

sequant-io/sequant#1640 · Opened Nov 3, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code Assessment (v2.1.303 → v2.1.316)
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 Over a week Newbie friendliness 8/100

sequant-io/sequant#1638 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.316 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 15/100

sequant-io/sequant#1637 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
feat: Hook change: Changed hook `if` conditions such as `Monitor(tail *)` to match the Monitor tool... (from Claude Code v2.1.314)
Open
- Is something wrong?
enhancement needs-triage upstream

Difficulty 4/5 3-5 days Newbie friendliness 12/100

sequant-io/sequant#1636 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
feat: Hook change: Fixed shell and MCP calls that auto mode, a deny rule or a PreToolUse hook block... (from Claude Code v2.1.314)
Open
- Is something wrong?
enhancement needs-triage upstream

Difficulty 4/5 3-5 days Newbie friendliness 12/100

sequant-io/sequant#1635 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.314 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 15/100

sequant-io/sequant#1634 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.312 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 15/100

sequant-io/sequant#1633 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.311 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 15/100

sequant-io/sequant#1632 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
qa: verdict lands as NEEDS_VERIFICATION with 'CI pending' as the only gap because /qa runs before the PR's checks finish
Open
- Is something wrong?
Difficulty 4/5 3-5 days Newbie friendliness 22/100

sequant-io/sequant#1630 · Opened Nov 2, 2026

Maintainers usually reply within 1 day
exec phase idles until run.timeout after the worker opened the PR, then reports 'Out of credits' from a stale rate-limit event
Open
- Is something wrong?
bug

Difficulty 4/5 3-5 days Newbie friendliness 42/100

sequant-io/sequant#1626 · 1 comment · Opened Oct 30, 2026

Maintainers usually reply within 1 day
feat(qa): a SEQUANT_AC marker in the QA skill — one machine-anchored line per criterion, read first by the #1525 producer, prose parse as fallback; retires the 80% parse (PROJECT-DISCUSSION §10)
Open
- Is something wrong?
enhancement graph-2026-10-review-surface

Difficulty 4/5 3-5 days Newbie friendliness 25/100

sequant-io/sequant#1622 · Opened Oct 28, 2026

Maintainers usually reply within 1 day
fix(ready): per-AC status is not recorded on the ready gate's QA phases — sequant ready and --ready-gate skip the #1525 producer, so the AC record goes stale after the gate
Open
- Is something wrong?
enhancement graph-2026-10-review-surface

Difficulty 4/5 3-5 days Newbie friendliness 38/100

sequant-io/sequant#1621 · Opened Oct 28, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code Assessment (v2.1.303 → v2.1.310)
Open
- Is something wrong?
assessment upstream

Difficulty 5/5 Over a week Newbie friendliness 25/100

sequant-io/sequant#1616 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat: Hook change: Windows: Fixed PreToolUse and PermissionRequest hooks letting a tool call throug... (from Claude Code v2.1.310)
Open
- Is something wrong?
enhancement needs-triage upstream

Difficulty 4/5 3-5 days Newbie friendliness 35/100

sequant-io/sequant#1615 · 1 comment · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.310 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 1/5 Under an hour Newbie friendliness 35/100

sequant-io/sequant#1614 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat: Hook change: Fixed hooks that run in PowerShell not blocking when the hook's program exits wi... (from Claude Code v2.1.309)
Open
- Is something wrong?
enhancement needs-triage upstream

Difficulty 4/5 3-5 days Newbie friendliness 35/100

sequant-io/sequant#1613 · 1 comment · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.309 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 3/5 1-2 days Newbie friendliness 35/100

sequant-io/sequant#1612 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.308 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 1/5 Under an hour Newbie friendliness 35/100

sequant-io/sequant#1611 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.307 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 1/5 Under an hour Newbie friendliness 25/100

sequant-io/sequant#1610 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.306 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

sequant-io/sequant#1609 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.305 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 45/100

sequant-io/sequant#1608 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat(skills): the human-surface reference — decisions via `AskUserQuestion`, waiting per mode, completion with a link; skills call `sequant comment render` and `sequant mutation …` instead of hand-rendering
Open
- Is something wrong?
graph-2026-10-ergonomics

Difficulty 5/5 Over a week Newbie friendliness 25/100

sequant-io/sequant#1606 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat(comments): `renderIssueComment` owns comment layout — headline and AC table visible, everything else in one `<details>` block; adopted by the QA verdict, merge-check and review-residue builders; hidden `sequant comment render` for skills
Open
- Is something wrong?
graph-2026-10-ergonomics

Difficulty 4/5 3-5 days Newbie friendliness 42/100

sequant-io/sequant#1605 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
chore(deps): one weekly grouped Dependabot batch per ecosystem — 20 of 39 Dependabot PRs in 60 days closed unmerged, superseded by regrouped bumps
Open
- Is something wrong?
Difficulty 2/5 1-3 hours Newbie friendliness 75/100

sequant-io/sequant#1601 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
chore(repo): prune the 149 merged remote branches and turn on `delete_branch_on_merge` after one verifying PR
Open
- Is something wrong?
Difficulty 4/5 1-2 days Newbie friendliness 25/100

sequant-io/sequant#1600 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
improve(ci): the `test` job is the whole CI wall clock (6.5–9.2 min of an 8.5-min median) — shard vitest across two runners or split the integration project into its own job
Open
- Is something wrong?
Difficulty 4/5 3-5 days Newbie friendliness 48/100

sequant-io/sequant#1599 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
bug(mcp): a sequant_run whose issues were all skipped by the state guard reports status success and passed: N — a skip is not a pass
Open
- Is something wrong?
bug

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sequant-io/sequant#1595 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
bug(run): text appended after the automated PR-body trailer is wiped by the next QA pass — isAutomatedPRBody treats "contains the trailer" as "wholly automated"
Open
- Is something wrong?
bug

Difficulty 3/5 1-2 days Newbie friendliness 54/100

sequant-io/sequant#1594 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
refactor(git): one runGit helper in git-diff-utils replaces the four local git() spawnSync wrappers
Open
- Is something wrong?
refactor

Difficulty 3/5 1-2 days Newbie friendliness 72/100

sequant-io/sequant#1592 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
refactor(workflow): no test seam defaults to a live GitHubProvider — one required provider on the issue context, set once where the context is built
Open
- Is something wrong?
refactor

Difficulty 4/5 3-5 days Newbie friendliness 55/100

sequant-io/sequant#1591 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat(review-residue): the Read-first comment links the QA verdict comment itself — postComment returns the comment URL
Open
- Is something wrong?
enhancement

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sequant-io/sequant#1590 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
fix(review-residue): the Tests line's printed command reproduces the class beside it (doMock, vi.mock(import()), the prose rule) and rendered paths are shell-quoted
Open
- Is something wrong?
bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

sequant-io/sequant#1589 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
test(review-residue): unit tests for the two runner paths — the PR-body SEQUANT_MUTATION merge and resolveReadFirstPR's state-record fallback with its open-PR guard
Open
- Is something wrong?
enhancement

Difficulty 3/5 1-2 days Newbie friendliness 55/100

sequant-io/sequant#1588 · Opened Oct 26, 2026

Maintainers usually reply within 1 day
feat: Hook change: Fixed a PreToolUse hook's deny reason being replaced by a timeout error when an ... (from Claude Code v2.1.304)
Open
- Is something wrong?
enhancement needs-triage upstream

Difficulty 5/5 Over a week Newbie friendliness 25/100

sequant-io/sequant#1584 · 2 comments · Opened Oct 23, 2026

Maintainers usually reply within 1 day
Upstream: Claude Code v2.1.304 Assessment
Open
- Is something wrong?
assessment upstream

Difficulty 4/5 3-5 days Newbie friendliness 35/100

sequant-io/sequant#1583 · Opened Oct 23, 2026

Maintainers usually reply within 1 day
fix(run): the PR body's imported exec text is cut at 4,000 characters with no marker — #1577 and #1578 both ended mid-word and read as complete
Open
- Is something wrong?
bug

Difficulty 2/5 1-3 hours Newbie friendliness 86/100

sequant-io/sequant#1582 · Opened Oct 23, 2026

Maintainers usually reply within 1 day
docs(windows): Sequant's bash hooks block every tool call on native Windows without Git Bash since Claude Code 2.1.299 — document it and make doctor fail
Open
- Is something wrong?
bug documentation upstream

Difficulty 3/5 1-2 days Newbie friendliness 73/100

sequant-io/sequant#1572 · Opened Oct 21, 2026

Maintainers usually reply within 1 day

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

sequant-io/sequant

Is sequant-io/sequant beginner-friendly?

How to contribute to sequant-io/sequant

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Is something wrong?

Showing the newest 100

Get new issues in your inbox