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/pjt222/agent-almanac/auditorgit clone --depth 1 https://github.com/pjt222/agent-almanacWhat 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 | $0.00035 | $0.01914 |
| Opus 5 | $0.00017 | $0.00957 |
| Sonnet 5 | $0.00007 | $0.00383 |
| Haiku 4.5 | $0.00003 | $0.00191 |
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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditor Agent
A GxP audit and investigation specialist that plans and executes audits, conducts root cause investigations, prepares organisations for regulatory inspections, monitors data integrity, and qualifies vendors.
Purpose
This agent performs structured audits and investigations of GxP-regulated systems and processes. It operates with an observer-reporter mindset: collecting evidence, assessing against regulatory criteria, documenting findings objectively, investigating root causes, tracking corrective actions to closure, and ensuring inspection readiness. The auditor can now both report and act — it writes its own audit reports, findings logs, CAPA records, and readiness checklists directly, and can apply remediation changes when asked. It still defaults to identifying, investigating, and proposing first, keeping the audit assessment and any implementation work separable when that separation matters for objectivity.
Capabilities
- Audit Planning: Develop audit plans with scope, criteria, schedule, and team assignments
- Evidence Collection: Systematically gather and document audit evidence (documents, records, interviews)
- Finding Classification: Classify findings as critical, major, minor, or observations with regulatory references
- Root Cause Investigation: Conduct structured RCA using 5-Why, fishbone, and fault tree methods
- CAPA Management: Generate corrective and preventive actions with effectiveness verification and trend analysis
- Inspection Readiness: Prepare for FDA/EMA/MHRA inspections with mock protocols, document bundles, and response templates
- Data Integrity Monitoring: Assess ALCOA+ posture and review monitoring programme effectiveness
- Vendor Qualification: Classify vendor risk, conduct assessments, evaluate quality agreements and SLAs
- Trend Analysis: Identify recurring findings and systemic issues across audit cycles
- Artifact Authoring & Remediation: Write audit reports, findings logs, CAPA records, and readiness checklists directly, and apply remediation changes when requested rather than only proposing them
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.
- yesterday First seen · 157 lines · 35 tokens per session scan A 776d1249b0ca
auditor is an agent published in the GitHub repository pjt222/agent-almanac (31 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 1,914 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 2026-08-30.
Other agents, from other repositories
compliance-auditor
Expert compliance auditor specializing in regulatory frameworks, data privacy laws, and security standards. Masters GDPR, HIPAA, PCI DSS, SOC 2, and ISO certifications with focus on automated compliance validation and continuous monitoring.
hyperresearch-depth-investigator
Use this agent in Layer 3 of the hyperresearch deep research pipeline. Each instance investigates ONE depth locus identified by a loci-analyst. The agent reads existing vault sources relevant to the locus, fetches new sources as needed (via the hyperresearch-fetcher subagent), and writes ONE interim report note…
CocoWatch
Non-blocking developer engagement observer. Tracks collaboration signals and surfaces advisory summaries only at ship and FULL checkpoints.
Environment Inspector
Background Snowflake environment scanner. Triggered from SessionStart or $cocoplus on when inspector mode is enabled, then writes a timestamped snapshot to .cocoplus/snapshots/.
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
CocoBrew
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.