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/yeisonrestrepo/code-conductor/cc-initgit clone --depth 1 https://github.com/yeisonrestrepo/code-conductorWhat 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 | $0.00011 | $0.00865 |
| Opus 5 | $0.00005 | $0.00432 |
| Sonnet 5 | $0.00002 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
cc-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1 — Detect project state
List files in the project (exclude .git/, .claude/, node_modules/, and dot-files, max depth 3). Count source files found.
If the count is 0 or only CLAUDE.md / config files exist, treat this as a new/empty project (IS_NEW=true). Otherwise set IS_NEW=false.
Step 2 — Auto-detect and collect project identity
Check if scripts/detect-stack.mjs exists in the project root. If it does, run:
node scripts/detect-stack.mjs "$PWD"
Environment flags: CC_GLOB_DEPTH and any other CC_* env vars the user may have set are automatically inherited by the child node process — no explicit export or forwarding is required. The /cc-init command must NOT reset or unset these variables before calling detect-stack.
Capture the JSON output. For each field in the JSON (name, description, stack, build, test, lint, format, setup), check the corresponding line in CLAUDE.md:
- If the CLAUDE.md line contains
<command>(any case) or is blank afterKey:→ replace with the detected value using a singleEditcall. - If the CLAUDE.md line already has a non-placeholder value → skip (never overwrite).
Apply all replacements in a single Edit call after collecting all detected values.
If scripts/detect-stack.mjs is missing or returns {}, skip auto-detection.
After auto-detection (or if skipped), check which identity fields remain blank:
Read CLAUDE.md. Check the ## Project Identity section.
If Name is still empty, ask the user all of these questions at once (not one at a time):
- What is the project name?
- One sentence: what does it do?
- Primary tech stack (e.g. "TypeScript + React", "Python + FastAPI") — only ask if
IS_NEW=falseAND stack was not auto-detected - Response language preference? (default:
en— only ask if context suggests otherwise)
If Name was already filled (by auto-detection or previous run), skip directly to Step 3 without asking.
Once any manual fields are collected, update CLAUDE.md with a single Edit call covering all remaining blank fields.
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 · 85 lines · 11 tokens per session scan A 481b332fa664
cc-init is a command published in the GitHub repository yeisonrestrepo/code-conductor (6 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 865 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
edit
Edit a stash item — inline replacement, or open in editor (preserves timestamp).
pop
Pop an item off the stash and continue working on it in the current session.
drop
Drop a stash item without working on it.
log
Show history of popped and dropped stash items.
show
Show a single stash item by number (for reading or copying its text).
list
Show all items currently in the stash.