Borrowing it
Nothing to install: this file belongs to nirelbaz/promptpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nirelbaz/promptpit/main/.claude/commands/audit-adapters.mdgit clone --depth 1 https://github.com/nirelbaz/promptpitWrote 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/commands/nirelbaz/promptpit/audit-adapters)<a href="https://agentmods.dev/commands/nirelbaz/promptpit/audit-adapters"><img src="https://agentmods.dev/badge/commands/nirelbaz/promptpit/audit-adapters.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 | $0.00000 | $0.00898 |
| Opus 5 | $0.00000 | $0.00449 |
| Sonnet 5 | $0.00000 | $0.00180 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
audit-adapters 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the AI Stack Expert agent definition at .claude/agents/ai-stack-expert.md to understand your role, expertise, and methodology. Then execute the following audit workflow.
IMPORTANT: This is a read-only audit. Do NOT modify any files — no code changes, no knowledge base updates. Read, compare, and report only.
Scope
$ARGUMENTS
If a specific adapter name was provided above (e.g., "cursor"), audit only that adapter. Otherwise, audit all adapters.
Phase 1: Read Current State
Read the following files to build your understanding:
Knowledge base:
- All files in
docs/knowledge/(or just the specified tool's file)
Adapter code:
src/adapters/types.ts— thePlatformAdapterandAdapterCapabilitiesinterfacessrc/adapters/registry.ts— which adapters are registeredsrc/adapters/adapter-utils.ts— shared translation and I/O utilities- Each adapter file:
src/adapters/claude-code.ts,src/adapters/cursor.ts,src/adapters/codex.ts,src/adapters/copilot.ts,src/adapters/standards.ts
Schema:
src/shared/schema.ts— Zod schemas and TypeScript types
Phase 2: Per-Adapter Analysis
For each adapter (tools where knowledge file has status: adapter-exists):
Compare what the knowledge base says the tool supports vs what the adapter code actually implements.
Check each dimension:
- Config paths — Is the adapter reading/writing to all correct file locations? Are there paths the tool supports that we miss?
- File formats — Are our translation functions producing valid output for the tool's current format?
- Feature coverage — For each feature (instructions, skills, agents, rules, MCP, hooks): does the tool support it? Does our adapter handle it? What's missing?
- Cross-tool reading — Does the knowledge base indicate this tool reads config from other tools? If so, is promptpit causing duplication by writing to both the tool's native config AND the shared config?
- Edge cases — Are known quirks from the knowledge base handled in the adapter code?
- Schema accuracy — Do our Zod schemas match the tool's real frontmatter/config format?
- Capabilities declaration — Does the
AdapterCapabilitiesobject accurately reflect the tool's real capabilities?
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.
- 7d ago First seen · 89 lines · 0 tokens per session scan A d375648e78ea
audit-adapters is a command published in the GitHub repository nirelbaz/promptpit (6 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 898 tokens. 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 commands, from other repositories
devbox-entrypoint
Context: runloop resumes a devbox by re-running the same entrypoint script, which invokes cn serve --id .... Because the entrypoint always replays, the CLI must avoid duplicating state on restart.
extract-profile
Extract a complete profile from an existing repo (runs the extract-profile skill).
rfc
Scaffold a new RFC in docs/rfc/proposed/.
memory-add
Capture a decision, learning, or incident note into project memory.
memory-reindex
Regenerate the project memory index after manual edits.
squadai-status
Run squadai status --json and display a rich project status summary.