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 skills add mrmps/chomsky-stack --skill grgit clone --depth 1 https://github.com/mrmps/chomsky-stackWrote 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/skills/mrmps/chomsky-stack/gr)<a href="https://agentmods.dev/skills/mrmps/chomsky-stack/gr"><img src="https://agentmods.dev/badge/skills/mrmps/chomsky-stack/gr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mrmps/chomsky-stack/gr"><img src="https://agentmods.dev/badge/skills/mrmps/chomsky-stack/gr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.01257 |
| Opus 5.5 | $0.00038 | $0.00503 |
| Sonnet 5.5 | $0.00019 | $0.00251 |
| Haiku 4.5 | $0.00010 | $0.00126 |
Grade A, and why
gr 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Greptile Review, Merge, and Deploy
Take the current PR from review through verified production deployment. Keep working until Greptile has no actionable findings, every current check is terminal without failures, GitHub reports the PR merged, the merged revision is deployed through the repository's documented production path, and production verification passes. A check being non-required does not make its failure safe to ignore.
Resolve the PR and base
- Read repository instructions and inspect the worktree before changing anything. Preserve unrelated user changes.
- Resolve the current PR with
gh pr view --json number,url,headRefName,baseRefName,mergeStateStatus,statusCheckRollup. - Fetch the PR base and head from
origin. - Review against
origin/<baseRefName>, never a possibly stale local base branch. Confirm the diff withgit diff --stat origin/<baseRefName>...HEAD. - If the branch is behind its remote base, rebase or merge according to repository convention before the final review. Use guarded force-pushes (
--force-with-lease) after rebasing.
Run Greptile
-
Confirm the CLI is available and authenticated with
greptile --versionandgreptile whoami. -
Inspect repository review rules with
greptile config. -
Run a fresh machine-readable review:
greptile review -b origin/<baseRefName> --json --instructions "Review rigorously for correctness, security, lifecycle races, data loss, performance regressions, error handling, and missing tests. Report every actionable issue; omit stylistic preferences." -
If Greptile reports an implausibly large diff, stop that run and fix base resolution. Do not split valid work merely to satisfy a review computed against stale local
main. -
Use
greptile review --resumeonly for an explicitly unfinished review. Use a fresh review after code changes.
Address findings
For every finding:
- Inspect the referenced code and surrounding contract.
- Classify it as actionable or false positive using concrete evidence.
- Fix actionable issues at the owning abstraction, add regression coverage, and avoid unrelated cleanup.
- Retain a concise evidence note for false positives; do not change correct code merely to silence a reviewer.
- Run focused tests after each logical fix.
What ships with it
1 file 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.
- 1mo ago First seen · 70 lines · 95 tokens per session scan A 438ccb386615
gr is a skill published in the GitHub repository mrmps/chomsky-stack (7 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,257 once invoked, about $0.0004 per session on Opus 5.5. 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
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…