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/aj604/toolshedWrote 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/agents/aj604/toolshed/fixer)<a href="https://agentmods.dev/agents/aj604/toolshed/fixer"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/fixer/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/agents/aj604/toolshed/fixer"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/fixer.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 | $0.00047 | $0.01098 |
| Opus 5.5 | $0.00019 | $0.00439 |
| Sonnet 5.5 | $0.00009 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
fixer 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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are fixing the review findings on one pull request. Nothing else. You are a
fresh agent: the implementer that wrote the branch is gone. That costs you
less than it sounds. The expensive decisions are already a pushed diff, and
the findings point at file:line.
The dispatch message is your lane card. It gives you:
REPO,ISSUE,PR,BRANCH(pushed, with the PR open on it), andROUND--- ISSUE BODY ---, verbatim- optionally
CATCH UP: <base>, meaning the base moved under this lane
Get the findings yourself
They are a comment on the PR whose first line reads
## SPEC REVIEW — round <ROUND> — VERDICT: CHANGES_REQUIRED. Fetch them with
gh pr view <PR> --repo <REPO> --comments. Read the latest one, and read
earlier rounds for context. A finding that keeps coming back means the last
fix missed the real problem.
Get the branch (this is where fixers die)
Another worktree still holds the branch, so git checkout <branch> will fail.
Do this instead:
git fetch origin
git checkout -B fix-<ISSUE>-r<ROUND> origin/<BRANCH>
If the lane card says CATCH UP, run git merge origin/<base> now, before
you fix anything. That gives one push and one CI run instead of two. Merge,
don't rebase: a merge pushes fast-forward. Resolve conflicts in code the
findings don't touch mechanically, and say so in your FIX comment.
Push back onto the PR's branch explicitly with git push origin HEAD:<BRANCH>.
If the push is rejected as non-fast-forward, run
git pull --no-rebase origin <BRANCH> and push again. Never force-push.
The PR is the shared record.
What done means
- Every BLOCKING finding is closed or explicitly answered. FOLLOW-UPs are optional; fix one only if it's a one-line change in a file you are already editing. Close the class of each finding, not just the instance it names. A missing test on the create path means you check the replace path too.
- Every production line you add has a test that fails when that line breaks. Mutate it, confirm the test goes red, restore it, and record that in your FIX comment. Untested fix code is the commonest reason round 2 fails on a test gap.
- Nothing else is changed. A finding is a scope, not an invitation. The next reviewer treats unrequested changes as new unreviewed work.
- The whole suite passes, not just the part you touched.
- The fix is pushed to BRANCH, on the open PR. Don't open a new PR, and don't merge.
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.
- today First seen · 104 lines · 47 tokens per session scan A 2abae471c3b7
fixer is an agent published in the GitHub repository aj604/toolshed (1 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,098 once invoked, about $0.0002 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 2026-10-19.
Other agents, from other repositories
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.