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.
git clone --depth 1 https://github.com/alinaqi/maggyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/alinaqi/maggy/icpg-bootstrap)<a href="https://agentmods.dev/commands/alinaqi/maggy/icpg-bootstrap"><img src="https://agentmods.dev/badge/commands/alinaqi/maggy/icpg-bootstrap.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00000 | $0.00418 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
icpg-bootstrap 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 7d 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
/icpg-bootstrap — Bootstrap from Git History
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
Usage
/icpg-bootstrap [--days N]
Default: 90 days of history.
Steps
1. Initialize iCPG if needed
icpg init
2. Run bootstrap
icpg bootstrap --days 90 --verbose
If no LLM API key available:
icpg bootstrap --days 90 --verbose --no-llm
3. Show results
iCPG BOOTSTRAP COMPLETE
═══════════════════════
History scanned: {N} days ({M} commits)
Commit clusters: {K}
ReasonNodes created: {R}
Symbols linked: {S}
Duplicates skipped: {D}
TOP INFERRED INTENTS:
1. [0.80] "Add JWT authentication" — 12 symbols, 5 files
2. [0.75] "Refactor payment processing" — 8 symbols, 3 files
3. [0.65] "Fix rate limiting bug" — 3 symbols, 2 files
...
LOW CONFIDENCE (review recommended):
- [0.55] "Update dependencies" — may be too generic
- [0.50] "Misc fixes" — commit message unclear
4. Offer review
Ask the user:
{N} ReasonNodes were inferred from git history. {M} are low-confidence and may need review.
Would you like to:
- Keep all (proceed with current quality)
- Review low-confidence intents (I'll show each one)
- Run drift scan now (
icpg drift check)
5. Post-bootstrap drift scan
icpg drift check
Show any immediate drift detected.
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.
- 7d ago First seen · 75 lines · 0 tokens per session scan A b53813a26d04
icpg-bootstrap is a command published in the GitHub repository alinaqi/maggy (705 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 418 tokens. 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 2026-08-30.
Other commands, from other repositories
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
ijfw-ship
Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.