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 harshanandak/forge --skill forge-reviewgit clone --depth 1 https://github.com/harshanandak/forgeWrote 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/harshanandak/forge/forge-review)<a href="https://agentmods.dev/skills/harshanandak/forge/forge-review"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-review/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/harshanandak/forge/forge-review"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00892 |
| Opus 5.5 | $0.00006 | $0.00357 |
| Sonnet 5.5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
forge-review 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-review
If a worker brief says stop after push or PR open, link an open PR to the issue, release the claim, then stop; leave thread linking and CI watching to the orchestrator.
Heavy proof
Before heavy or critical PRs, read forge route get review --text. Count it with forge issue call <slice> --role review; LIMIT_REACHED stops the intent. Retry REVISION_CONFLICT. Pass returned timeboxMinutes and stopBy. Tell the subagent to stop and report the checkpoint when timeboxMinutes expire, never later than stopBy. Use the route to review the diff, saved trunk/head scenario output and every acceptance item in fresh context. Save findings/evidence on the slice, with single-family if returned; never claim another family.
Each push: checkpoint review SHA/time, round in next, before replies.
On each wake: conflicts, then threads, then CI
- On wake, run
forge pr state <n>and act onverdict. Read checkpoint's last push SHA/time and round before triage. Usegh pr update-branch <n>only for a clean behind-base update. For conflicts, merge base locally, resolve, commit, runforge-build's Final-head proof, then push. Never rebase a pushed branch or force-push. - Get
<owner> <repo>fromgh repo view --json owner,name. List unresolved threads:node <skill-dir>/list-threads.mjs <owner> <repo> <n>. Read full comments and timestamps withgh api repos/{owner}/{repo}/pulls/<n>/comments --paginatebefore deciding. - Triage only comments and checks newer than the last push. Verify an old thread is fixed at head before closing with
Fixed in <sha>. Other old threads wait for new evidence; age never justifies resolution.
Each finding
- Check the source; bots can be wrong. Cite the line that shows it.
- Fix only P0, P1 findings on lines this PR changed, inside the slice's done boundary.
- Everything else (P2, P3, or outside the boundary) is filed, not fixed. Search open issues for the symptom, then comment on a match or
forge issue create --input '{"title":"...","kind":"task","labels":["review-deferred","p2"],"parent":"<epic>","body":"from <pr url> thread <id>"}'. - Batch and commit thread/CI fixes. Run
forge-build's Final-head proof section on that commit, then send one push wave.
What ships with it
3 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.
- yesterday Changed · -4 lines f27549a0e14c
- 2d ago First seen · 49 lines · 16 tokens per session scan A 579f53492f4e
forge-review is a skill published in the GitHub repository harshanandak/forge (0 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 892 once invoked, about $0.0001 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 2026-10-28.
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…