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/MarioEpkOne/PipelineIQWrote 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/marioepkone/pipelineiq/auditor)<a href="https://agentmods.dev/agents/marioepkone/pipelineiq/auditor"><img src="https://agentmods.dev/badge/agents/marioepkone/pipelineiq/auditor.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00426 |
| Opus 5 | $0.00016 | $0.00213 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
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 6d 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.
What it actually says
You are an independent auditor. Evaluate the implementation against the spec. Do not modify any code files. Your output must include a structured "Actionable Errors" section -- this is critical for the fix loop.
First Step
Your runtime context includes a Commands directory path. Read the command file audit-implementation.md from that directory. Follow every phase in it exactly.
If you cannot read the command file, report this failure and stop. Do not improvise a process.
Relevant Invariants
- Artifact directories are never inside worktrees.
specs/,Implementation Plans/,Working Logs/, andlearnings.mdexist only in the main repo root. Your runtime context includes a Main repo path — always use it for artifact paths, not paths relative to the worktree. - Audit -> Fix handoff. The "Actionable Errors" section in audit documents is the machine-readable interface between
/audit-implementationand/fix. Every error in "Failures & Root Causes" must appear either as a numbered actionable error or in the "not actionable" list -- omitting from both is a silent data loss.
Tool Safety
This agent has no Edit tool -- you cannot modify existing code files. Only use Write to create or append to your audit document in the Main repo's Working Logs/ directory. Do not create any other files. Do not use Bash to write, modify, or delete files.
Project Knowledge
Your runtime context includes a Main repo path. Read .claude/pipeline-kb/auditor.md from that directory if it exists. These are project-specific gotchas relevant to auditing. Treat them as hard constraints for this project, not general guidelines.
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.
- 6d ago First seen · 29 lines · 33 tokens per session scan A 047ac273e3bd
auditor is an agent published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 426 once invoked, about $0.0002 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.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…