Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/pcopu/coco/coco-deliverynpx skills add pcopu/coco --skill coco-deliverygit clone --depth 1 https://github.com/pcopu/cocoWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.00349 |
| Opus 5 | $0.00032 | $0.00175 |
| Sonnet 5 | $0.00013 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
coco-delivery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
CoCo Delivery Skill
Ship CoCo changes with a consistent workflow and repo-aware checks.
When to Use
Use this skill when making behavior changes in this repository, especially for:
- slash commands and callback menus
- app-server send paths
- queueing, steer, and watchdog behavior
- session/worktree lifecycle flows
- status/usage/model panels
- allowlist and approval UX
When NOT to Use
Do not use this skill for:
- unrelated Python projects
- one-off shell tasks not tied to
CoCo - docs-only edits with no bot/runtime behavior impact
Workflow
- Locate the flow entrypoints.
- Patch the smallest safe surface first (helpers before handlers).
- Add or update targeted tests.
- Run focused tests for touched areas.
- Run full test suite before finalizing.
Use references/file-map.md for file touchpoints and references/test-matrix.md for test commands.
Guardrails
- Prefer
rgfor code discovery. - Keep queue and status behavior thread/topic-safe.
- Keep queue and status behavior aligned with app-server flows.
- Add telemetry for new failure/retry branches.
- Avoid broad refactors while shipping feature requests.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 48 lines · 65 tokens per session scan A 7f75416dfb09
coco-delivery is a skill published in the GitHub repository pcopu/coco (4 stars, last pushed 9d ago), licensed MIT. It adds 65 tokens to every session and 349 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
add-new-agent-support
Add a new agent (tool) support to agent-command-sync following the registry pattern.
with-config
A Codex skill with openai.yaml configuration.
standard-skill
A standard test skill for Gemini.
test-skill
A test skill for chimera.
basic-skill
A basic test skill for Claude.
watching-ai-format-evolution
Use when manually monitoring, watching, tracking, or reviewing AI assistant storage, session, transcript, JSONL, or SQLite format drift after official upstream repository, changelog, or package updates, especially when fixtures, parser docs, tests, or parsers may be stale.