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 commands/cypsy1714/cchad/initgit clone --depth 1 https://github.com/Cypsy1714/cchadWhat 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 | $0.00016 | $0.00184 |
| Opus 5 | $0.00008 | $0.00092 |
| Sonnet 5 | $0.00003 | $0.00037 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
init 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
Help the user configure Claude Code for the current repository with cchad.
- Run
uvx cchad plan --jsonin the current working directory with the Bash tool and read the JSON plan. - Summarize it in chat: the packages to add (id, scope, why) and the ones deliberately skipped (with reason).
- Ask the user to confirm.
- On confirmation, run
uvx cchad init --yeswith the Bash tool. - Surface any manual steps from the output (cchad never runs installers itself).
- Tell the user to reload Claude Code (or restart) so the new MCP servers and
skills load, and to commit
auto_plugins_mcps.mdso teammates get the same setup.
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 · 15 lines · 16 tokens per session scan A 6df36574da2e
init is a command published in the GitHub repository Cypsy1714/cchad (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 184 once invoked, about $0.0001 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 commands, from other repositories
execute
Execute queued goal chunks with capacity-aware workers.
self-dispatch-test
Nondestructive OpenCode orchestrator self-dispatch verification.
build-corpus
Build or refresh the private dispatch-context corpus.
validate-dispatch
Render and validate a dispatch wrapper without launching it.
agent-audit
Packaging readiness audit — score an AI agent across 6 dimensions before packaging it.
agent-guide
Orientation and routing for AI agent packaging — assess what you built, see the full journey, get a personalized roadmap.