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/nrdxp/predicate/api-auditnpx skills add nrdxp/predicate --skill api-auditgit clone --depth 1 https://github.com/nrdxp/predicateWhat 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 | $0.00049 | $0.03327 |
| Opus 5 | $0.00024 | $0.01664 |
| Sonnet 5 | $0.00010 | $0.00665 |
| Haiku 4.5 | $0.00005 | $0.00333 |
Grade A, and why
api-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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Coherence Audit Protocol
A thorough, piecemeal framework for auditing code API surfaces. Designed to maintain agent coherence by working iteratively through the codebase with explicit human checkpoints.
Adversarial path anchor. This lens is invoked on the Verification Dual's adversarial path (rules.md §2 Invariant 1): when no deterministic evaluator can close an API-surface correctness condition, context-free agents using this protocol supply the decorrelated review. See skills/refine/SKILL.md AUDIT §"Sibling Skills Consultation" for the wiring point.
Guiding Principle: An ideal API is minimal, well-scoped, type-safe, elegantly composable, and monosemic. It leverages language features to make error states unrepresentable.
Phase 0: Scope Definition
Before beginning, establish the audit scope with the user. Confirm: target language and version; type system strength; public API entry points; explicit exclusions (generated code, vendored deps); user-defined constraints (e.g., no breaking changes, no-std compatibility).
Checkpoint: Present scope to user for approval before proceeding.
Phase 1: Surface Discovery (Full Codebase Ingestion)
Objective: Build a complete mental model of the public API surface before any analysis.
1.1 Enumerate Public Surface
For each entry point, catalog:
- Exported Types: Structs, enums, classes, interfaces, type aliases
- Exported Functions: Free functions, associated functions, methods
- Exported Constants: Public constants, static values
- Re-exports: Items re-exported from internal modules
- Traits/Interfaces: Abstractions meant for external implementation
1.2 Generate Surface Map
Produce a structured inventory:
## Module: `crate::auth`
### Types
- `Principal` (struct) — L23-L45
- `AuthState` (enum) — L47-L62
### Functions
- `Principal::verify(&self, sig: &Signature) -> Result<()>` — L67
- `validate_token(token: &str) -> Result<Claims>` — L89
### Traits
- `Authenticator` — L12-L21
- `fn authenticate(&self, credentials: &Credentials) -> Result<Session>`
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 · 348 lines · 49 tokens per session scan A 28c4172225ae
api-audit is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 49 tokens to every session and 3,327 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…