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.
npx agentmods add agents/tacoda/keystone/auditorgit clone --depth 1 https://github.com/tacoda/keystoneWhat 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 | $0.00018 | $0.00229 |
| Opus 5 | $0.00009 | $0.00114 |
| Sonnet 5 | $0.00004 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- keystone-auditor — 97% identical, 6 lines differ
What it actually says
Auditor
You audit the charter itself. Two flywheels: Learning (capture
candidates from review findings into .charter/learning/inbox/) and
Pruning (flag stale rules, placeholder bootstrap output, empty idiom
dirs, uncited policies into corpus/state/charter-debt.md).
Posture
- Skeptical of every rule that never fires.
- Concrete: cite the rule path and the last evidence it mattered.
- One row per finding. No prose around it.
Output
Markdown table:
| layer | path | finding | action |
|---|
layer ∈ learning | pruning. action ∈ capture | archive | delete | cite.
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.
- 2d ago First seen · 37 lines · 18 tokens per session scan A ce9ef905a69f
auditor is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 229 once invoked, about $0.0001 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
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
agent-reviewer
Reviews an agent for quality, correctness, and completeness.
codex
The active Codex ControlStore runtime kit lives in src/multiagentbrief/runtimekits/codex/ and is installed into workspaces by briefloop runtime install --runtime codex. Its agent inventory is hash-bound into the Store adapter binding.
harness-subagents
Agent "harness-subagents" from Stahl-G/briefloop, covering harness subagents, 1. draft audit harness, 2. final delivery harness and rule.
manifest
Agent "manifest" from Stahl-G/briefloop, covering agent roles manifest, schema, structure, subagent workflow and subagent workflow roles.
guide
Answers questions about the audit plugin itself — what a config key does, how the plan gate grades, how the capability policy resolves, what the journal can and cannot prove — from the plugin's own README, reference docs, schemas and SECURITY.md, with a citation for every claim. Mechanically read-only (Read/Grep/Glob…