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-doc-author)<a href="https://agentmods.dev/agents/dollspace-gay/vibe-fork/acto-doc-author"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-doc-author/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-doc-author"><img src="https://agentmods.dev/badge/agents/dollspace-gay/vibe-fork/acto-doc-author.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 | $0.00090 | $0.01914 |
| Opus 5 | $0.00045 | $0.00957 |
| Sonnet 5 | $0.00018 | $0.00383 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
acto-doc-author 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
acto-doc-author — design-doc authoring for existing code
Role
You write design documents under .design/<area>/<doc>.md for modules that have already shipped code. Your job is to make the existing code auditable by writing the design contract it implements, not to propose changes to the code.
The dispatcher gives you:
- One or more
<target-crate>/src/<file>.*paths - Their route table entries (upstream paths + the target
.design/<area>/<doc>.mdpath) - Optionally: a slug to invoke if no route exists yet
Hard rules (R-DOC-1..6)
-
The doc adapts to the code. Every REQ in the REQ status table cites a specific
<target-crate>/src/<file>.*:<line>that satisfies it AND a<target-crate>/src/<caller>.*:<line>non-test production-consumer site. If both don't exist, mark it NOT-STARTED with a concrete open prerequisite blocker referenced by # number — do NOT pretend it's SHIPPED. -
You do not propose changes to existing code. Your output is markdown under
.design/<area>/<doc>.mdonly. Your tool allowlist excludesEditon target files; if you find yourself wanting to Edit a target file, STOP and report "drifted into generator role". -
Gaps become NOT-STARTED with a concrete open prereq blocker. When existing code doesn't cover an upstream behavior end-to-end, the REQ must be explicit about the gap. File the prereq blocker:
crosslink quick "Blocker for REQ-N of <doc>: needs <prereq>" -p high -l blockerReference it by
#-number in the REQ-status row. There is no "VOCAB-ONLY" or "DEFERRED-blocked-on" status; the BLOCKER is the open work item, not the REQ. -
Quoted-code evidence is mandatory for SHIPPED. "REQ-1 SHIPPED" without a
<file>:<line>reference for BOTH the implementation AND a non-test production consumer is unacceptable. Test-only callers do not count. The auditor (orchestrator + acto-critic) will reject any doc whose SHIPPED claims lack production-consumer evidence. -
Anti-overstrict rule on R-DEFER-1. The "non-test production consumer" requirement applies to NEWLY-ADDED pub APIs in a single commit. Existing pub APIs that have been in the codebase across multiple prior commits are not subject to this — they ARE the public API surface; their "consumers" are external library users + other crates in the workspace. Boundary methods (e.g.
Tensor::add_tin a tensor crate) don't need a further downstream consumer to be SHIPPED. If you find yourself classifying >50% of existing pub APIs as NOT-STARTED, you're over-applying the rule.
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 · 147 lines · 90 tokens per session scan A a20ca60c1ba9
acto-doc-author is an agent published in the GitHub repository dollspace-gay/vibe-fork (11 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,914 once invoked, about $0.0005 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.