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 commands/adilkalam/orca/auditgit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00009 | $0.07671 |
| Opus 5 | $0.00005 | $0.03836 |
| Sonnet 5 | $0.00002 | $0.01534 |
| Haiku 4.5 | $0.00001 | $0.00767 |
Grade B, and why
audit scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .orca/audit/temp/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 833 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit - Due Diligence Codebase Auditing
Philosophy: Investor-grade quality assessment. This command evaluates quality, consistency, and risk through direct evidence-based verification. Every finding includes the claim checked, the verification performed, and the result.
Independent from pipelines: /audit is NOT a gate or verification agent. It's a standalone diagnostic tool that runs independently of /ios, /nextjs, etc.
Direct execution: All verification is performed directly by the executing agent using a structured process schema. No subagent delegation. Evidence trails make verification work transparent and gaps detectable.
Verbose Flag
Include verbose: false in every cognition MCP call from /audit. This is a multi-call command; the minimal ACK response saves tokens.
Command Modes
# Quick health check (~10 min) - 3 core dimensions
/audit
# Full due diligence audit (~60-90 min) - all dimensions
/audit --comprehensive
# Core dimensions only (~25 min) - 5 dimensions
/audit --core
# Focused audit on specific area (~10-15 min)
/audit --item design-system
/audit --item page /checkout
/audit --item data
/audit --item module auth
/audit --item infra
# Deep documentation verification (~20-30 min) - samples key docs, all 6 ops
/audit --documentation
# Exhaustive documentation verification (no time limit) - every file, every line
/audit --documentation --comprehensive
# Incremental audit since commit
/audit --since abc1234
# Verbosity
/audit --verbose # Full findings (default: TL;DR only)
Invalid combinations: --documentation --since is not supported (error: documentation verification requires full file reads, not diffs).
Quality Dimensions
| # | Dimension | Weight | Execution Order |
|---|---|---|---|
| 1 | Structure Quality | 0.10 | 1st |
| 2 | Security Posture | 0.20 | 2nd |
| 3 | Dependency Health | 0.15 | 3rd |
| 4 | Pattern Consistency | 0.10 | 4th |
| 5 | Architecture Health | 0.15 | 5th |
| 6 | Test Quality | 0.15 | 6th |
| 7 | Documentation Quality | 0.10 | 7th |
| 8 | Design Integrity | 0.05* | 8th |
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 · 833 lines · 9 tokens per session scan B 2d1617279ba2
audit is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 7,671 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.