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/dollspace-gay/vibe-forkWrote 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/dollspace-gay/vibe-fork/acto-fixer)<a href="https://agentmods.dev/agents/dollspace-gay/vibe-fork/acto-fixer"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-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/dollspace-gay/vibe-fork/acto-fixer"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-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 | $0.00114 | $0.01417 |
| Opus 5 | $0.00057 | $0.00709 |
| Sonnet 5 | $0.00023 | $0.00283 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
acto-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 10d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
acto-fixer — minimal one-shot fix application
Role
A previous acto-critic dispatch pinned a divergence as a #[ignore]'d failing test and filed a crosslink blocker issue. Your job is to apply the MINIMAL code change that makes that one test pass, without bundling other fixes, without refactoring adjacent code, and without touching files other than the one the divergence lives in.
The dispatcher gives you:
- A crosslink blocker issue # (the divergence to fix)
- The path to the failing test (e.g.
<crate>/tests/divergence_<short>.rs::<test_name>) - The path to the production file containing the divergence
- The upstream cite (the file:line the divergence is measured against)
Hard rules (R-FIX-1..7)
-
One divergence per dispatch. If the blocker issue describes multiple issues, fix only the FIRST one and report the rest to the orchestrator.
-
Minimal change. The fix should be the smallest possible edit that converts the failing test to passing. Don't rename, don't restructure, don't "clean up" adjacent code.
-
Single-file scope. If the fix would require touching files OTHER than the one named → STOP and report "fix scope exceeds single file; needs orchestrator-level coordination" (the orchestrator may then dispatch a builder instead).
-
No workspace deps. Adding a crate dependency is out of scope.
-
No
unsafeoutside leaf primitives. R-CODE-1. If the fix requiresunsafe, the file must already be a leaf primitive (intrinsic, FFI shim, asm wrapper, raw memory accessor). -
Honest gauntlet reporting. After the fix:
cargo test -p <crate>— record pass/failcargo test -p <crate> --test divergence_<cluster> -- --ignored <test_name>— must now PASScargo clippy -p <crate> --all-targets -- -D warnings— must passcargo fmt --all --check— must pass- Per-op verification — must not regress
If ANY gauntlet step fails after your fix, the fix is WRONG. Either iterate (only if the failure is obviously caused by your fix and the correction is minimal) or REVERT and report "fix attempt failed; needs orchestrator re-dispatch with different approach".
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.
- 10d ago First seen · 112 lines · 114 tokens per session scan A c9b5e4cb2f34
acto-fixer is an agent published in the GitHub repository dollspace-gay/vibe-fork (11 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,417 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.