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 skills/conn-castle/agent-layer/interface-auditnpx skills add conn-castle/agent-layer --skill interface-auditgit clone --depth 1 https://github.com/conn-castle/agent-layerWhat 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 | $0.00055 | $0.00522 |
| Opus 5 | $0.00028 | $0.00261 |
| Sonnet 5 | $0.00011 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
interface-audit 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interface-audit
Produce one evidence-backed audit of product interface boundaries. Do not implement or launch planning.
Inputs and references
Run a fresh audit by default. --update [report-path] refreshes an existing
report. Read references/report-structure.md; for an update also read
references/update-workflow.md.
A fresh audit uses only current code, tests, docs, command output, and evidence created for this run. Do not inspect prior audit artifacts unless the user asks for an update.
Evidence contract
- Score concrete component boundaries, not vague subsystems.
- Verify names and numeric claims; use
partialwhen exact measurement adds little value. - Ground complexity, over-engineering, debt, confidence, and recommendations in current evidence. Current code and tests outrank stale documentation.
- Preserve row identifiers during updates and never reuse retired identifiers.
- Protect discovered product requirements unless the user approves a behavior change. Do not preserve stale scores for continuity.
Workflow
- Establish fresh or update mode, repository baseline, report path, and scope.
- Trace the interface chain, contracts, ownership, state, tests, failure modes, and meaningful cleanup opportunities. Investigate directly unless coherent, independent boundary groups benefit from read-only parallel investigation.
- Calibrate neighboring rows, update the report, and select the highest-value
coherent improvement. Revisit only evidence gaps or inconsistencies. If no
candidate justifies its cost, record
no-material-improvement. - For a material candidate, decide whether it requires broad ownership,
protocol, data-model, cross-language, or user-workflow redesign. Recommend
that architecture only when a smaller interface improvement is insufficient;
otherwise recommend the smallest coherent improvement. State any behavior
change and require approval before it enters a plan. Include exact
/implementinput as a handoff, but do not run it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 55 tokens per session scan A fa9bfa2ef186
interface-audit is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 522 once invoked, about $0.0003 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 skills, from other repositories
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.