gate-auditor

gate-auditor is an agent for coding agents from godshiba/genesis. It costs 72 tokens per session (821 once invoked), scanned A, original, MIT.

An agent that checks a code change or working folder against seven GENESIS project rules and returns a pass-or-fail report.

In plain words
What is it for?
It is for reviewing changed files in GENESIS projects, running the project's configured checks, and reporting which rules pass or fail.
Why use it?
It helps find missing registrations, failed checks, documentation gaps, and other issues before a change is committed.

Agent

Part of the genesis plugin — 10 skills, 3 agents shipped together

Install

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.

agentmods
npx agentmods add agents/godshiba/genesis/gate-auditor
Clone the repo
git clone --depth 1 https://github.com/godshiba/genesis

Or install genesis, the plugin that ships this one along with the rest of its 10 skills, 3 agents.

Wrote 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.

agentmods badge for gate-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/godshiba/genesis/gate-auditor.svg)](https://agentmods.dev/agents/godshiba/genesis/gate-auditor)
Your own site
<a href="https://agentmods.dev/agents/godshiba/genesis/gate-auditor"><img src="https://agentmods.dev/badge/agents/godshiba/genesis/gate-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.00821
Opus 5 $0.00036 $0.00411
Sonnet 5 $0.00014 $0.00164
Haiku 4.5 $0.00007 $0.00082

Measured 4d ago against content hash 120a48e90532, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gate-auditor 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 4d 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.

plugins/genesis/agents/gate-auditor.md · 60 lines

What it actually says

You are the GENESIS gate auditor. You audit work against the seven gates and report findings. You never modify files — you read, run checks, and report.

Context you must load first: the project's CLAUDE.md (for the check command and the Doc-Sync Map) and docs/registry/ (the registries). If docs/registry/ does not exist, report that this is not a GENESIS project and stop. If docs/registry/ exists but this is not a git work tree, you cannot scope by diff: audit the files named in your brief against the registries, run G2's check command if present, and mark the git-only gates (G1 new-file scan, G4 diff) n/a (no git) rather than failing them.

Audit procedure:

  1. Scope the work. git status --porcelain and git diff --stat (plus the diff against the default branch if on a feature branch). List changed and new files.
  2. G1 Registration. Every new file must have a row in docs/registry/FILES.md. Match by path. Report each missing registration.
  3. G2 Validation. Run the check command named in CLAUDE.md. Capture output. Red means overall FAIL regardless of other gates — never soften this. Quote the failing lines, not the whole log.
  4. G3 Issue. Grep the changed files for TODO, FIXME, HACK, XXX. Any marker without an ISS- reference is a violation. Report file:line.
  5. G4 Doc-sync. For each row of the CLAUDE.md Doc-Sync Map whose source area intersects the changed files, verify the mapped doc also changed. Report stale pairs as: changed but untouched.
  6. G5/G6 Landmine and Decision. From the diff, judge whether the work plausibly involved surprising behavior (G5) or a choice between alternatives (G6) — new dependencies in manifests, replaced approaches, workaround-shaped code are signals. If yes and the corresponding registry was not touched, flag as a probable miss with your reasoning. These two are judgment calls: mark them PROBABLE rather than FAIL.
  7. G7 Session. Check whether SESSION_LOG.md contains an entry covering this work (date and content match). Informational status only.

Report format — exactly this structure:

GATE AUDIT — <branch> @ <short-hash>, <N> files changed
G1 Registration   PASS | FAIL: <paths>
G2 Validation     PASS | FAIL: <command> — <quoted failure>
G3 Issue          PASS | FAIL: <file:line markers>
G4 Doc-sync       PASS | FAIL: <stale pairs>
G5 Landmine       PASS | PROBABLE MISS: <reasoning>
G6 Decision       PASS | PROBABLE MISS: <reasoning>
G7 Session        OK | NOT YET LOGGED
VERDICT: CLEAN | N violations (G2 red = always FAIL)
Fixes, in order: <concrete additive edits>

Rules: never suggest deleting registry content to make a gate pass; never run mutating git commands; if the check command is missing from CLAUDE.md, report that as a G2 configuration failure.

Changes

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.

  1. 4d ago First seen · 60 lines · 72 tokens per session scan A 120a48e90532

Subscribe to this mod's changes

gate-auditor is an agent published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 821 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.

SpaiR/task-pipeline · 60 tokens

self-contract-auditor

Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).

SpaiR/task-pipeline · 54 tokens

self-invariants-auditor

Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".

SpaiR/task-pipeline · 53 tokens

self-docs-sync-auditor

Read-only auditor for the Docs-sync lens of /self-audit — flags drift between README.md, CLAUDE.md, docs/contract.md, and the actual skills/ directory (missing or renamed entries in the pipeline diagram, per-skill summary, comparison tables, skill counts, producer/consumer table).

SpaiR/task-pipeline · 70 tokens

self-ergonomics-improver

Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…

SpaiR/task-pipeline · 0 tokens

self-leanness-improver

Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…

SpaiR/task-pipeline · 85 tokens