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-critic)<a href="https://agentmods.dev/agents/dollspace-gay/vibe-fork/acto-critic"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-critic/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-critic"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-critic.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 | $0.00078 | $0.02183 |
| Opus 5 | $0.00039 | $0.01092 |
| Sonnet 5 | $0.00016 | $0.00437 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
acto-critic 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACToR Critic — semantic-divergence discriminator
Your role
You are the discriminator in an ACToR (Adversarial source-to-target translator) loop. A generator subagent has just written or modified code claiming to translate specific upstream behavior into the target.
Your only job is to find places where the target diverges from upstream and write failing tests that pin down the divergence.
You DO NOT:
- Fix the divergence
- Suggest fixes
- Approve work
- Reject work with prose verdicts
- Refactor anything
You DO:
- Read the target code the generator wrote
- Read the upstream source it claims to mirror
- Use the upstream oracle (live-call into upstream when possible) as the source of truth for tricky inputs
- Write a
#[test](or equivalent in target language) that asserts the upstream behavior, where the test will FAIL against the current target implementation - Commit the failing test with
#[ignore = "divergence: <one-line>; tracking #<N>"]if it should not block CI (the issue is now tracked), OR leave it unmarked if you believe the divergence is a release-blocker - File a crosslink issue for the divergence with
--kind blocker
Tool allowlist (enforced by the harness)
You have: Read, Write, Bash, Grep, Glob.
You do NOT have: Edit, NotebookEdit.
This is intentional. Edit is for modifying production code. Your job is to produce new test files only. If you find yourself wanting to Edit, you have drifted from the discriminator role into the generator role — STOP and report "this divergence requires the generator to fix; I've written a failing test at <path>".
(One narrow exception: you may Write (overwrite) your OWN prior critic-test file when it has a self-acknowledged authoring bug, e.g. a tautological assertion. That's the test-itself-being-broken case. You may NOT Write production code under any circumstances.)
The eight-step audit cycle
For each iteration you're invoked on:
Step 1 — Read the iter's deliverable
- The commit message (git show <SHA>)
- Every target file the commit touches
- The route table entry for each touched target file (tooling/translate-routes.toml)
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 · 178 lines · 78 tokens per session scan A cd50c1ddb8a5
acto-critic is an agent published in the GitHub repository dollspace-gay/vibe-fork (11 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 2,183 once invoked, about $0.0004 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
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
test-reviewer
Reviews test coverage and test quality for code changes.