[dogfood][first-run][main] README count drift: "947 total assets", "Core skills (66)" lists 63 of 74, "70 expertise cells" (registry has 98)

Open
#245 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
75/100
Issue type
Bug
Clarity
Clearly specified
Activity status
Active
Tech stack
json, markdown, python, shell

Research direction

Start with README, docs/asset-counts.json, systems/superintelligence/registry.json, and tests/check-asset-counts.sh; inspect build-index.py as the suggested source for derived values. Compare the documented totals, core-skill list, and cell count with the registries, then run the existing asset-count check and confirm all three discrepancies are covered.

Written by the indexing model from the issue text.

Description

dogfood P2

Path: main 829f516
Adapter: n/a (README)

Command

python3 -c "import json;print(json.load(open('docs/asset-counts.json')))"
# README "Core skills (N)" list vs skills/*/SKILL.md; cells from systems/superintelligence/registry.json

Expected: every count in README matches or derives from docs/asset-counts.json and the registries. tests/check-asset-counts.sh doesn't cover these three.

Actual

  1. 947 total assets (L231 "up to 947 total assets", L724 "Total Addressable Assets: 947"). No combination of asset-counts gives 947: skills+commands+agents+rules+workflows = 226+386+35+15+3 = 665, and adding 495 personas gives 1,160.
  2. "Core skills (66)" (L283) under "every one of the 226 skills" (L279). The list has 63 names, while asset-counts core = 74. Missing from the list: agent-self-eval, arch-index, coco-diagram, coco-ship, context-budget, goal, humanizer, journey-map, karpathy-guidelines, local-llm, visual-explainer. The "full catalog" also leaves out the cognee, hyperframes, and m0 bundles.
  3. "70 expertise cells" (L122, L720 "495 across 13 departments and 70 cells"). The meta-registry has 98 cells: ai 8, engineering 11, product-design 8, trading 8, the other nine teams 7 each.

Output

asset-counts: skills 226 (core 74) / commands 386 / agents 35 / rules 15
README "Core skills (66)" lists 63 names; skills/ with SKILL.md: 74
cells (sum of meta-registry cells): 98

Suggested fix: derive 947, the core list, and the cell count from build-index.py output, and add them to check-asset-counts.sh.

Found by: Raini (SI PM) first-run dogfood, 2026-09-24

Dominant language
HTML
Stars
347
Forks
12
Avg merge
2d 16h
Merged PRs (30d)
95

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from coco-research/coco

All issues in coco-research/coco

Similar issues

More Documentation issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.