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 skills add marcoguillermaz/Tierward --skill api-contract-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/skills/marcoguillermaz/tierward/api-contract-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/api-contract-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/api-contract-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/api-contract-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/api-contract-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.03946 |
| Opus 5 | $0.00039 | $0.01973 |
| Sonnet 5 | $0.00016 | $0.00789 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
api-contract-audit scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read Glob Grep Bash(curl:*) Bash(git:*) How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope for v1
- Static analysis only. Parses OpenAPI spec files on disk or auto-generated output captured from the running dev server. Does not execute request traffic against endpoints, does not diff runtime responses, does not validate live SLAs.
- Richardson Maturity Model L0-L3. L0 (RPC over HTTP), L1 (resource URLs), L2 (correct HTTP verbs), L3 (HATEOAS). L3 detection is best-effort via response-schema inspection for
_links,rel,href, JSON:API, or HAL patterns. - Spec diff requires git history. Breaking-change detection compares the current spec vs the previous committed version via
git show HEAD~1:<spec-path>. Falls back to no-diff mode when git history is unavailable.
Configuration (adapt before first run)
Replace these placeholders:
[OPENAPI_SPEC_PATH]- location of the OpenAPI spec if committed on disk (e.g.openapi.yaml,api/openapi.json,docs/openapi.yaml). Leave empty to rely on framework auto-gen.[API_SOURCE_PATH]- path to API route handlers (e.g.src/routes/,app/api/,src/controllers/).[DEV_SERVER_URL]- optional, for framework auto-gen fallback (e.g.http://localhost:3000). Leave empty to skip runtime spec fetch.
Step 0 - Target and mode resolution
Parse $ARGUMENTS for target: and mode: tokens.
| Pattern | Meaning |
|---|---|
target:spec:<path> |
Audit a specific spec file (target:spec:api/v2.yaml) |
target:endpoint:<path> |
Audit a single endpoint path (target:endpoint:/users/{id}) |
mode:drift |
Run only AC1-AC3 (endpoint / schema / status drift) |
mode:richardson |
Run only AC8 (Richardson Maturity scoring) |
mode:all / no argument |
Full audit (AC1-AC8). |
STRICT PARSING: derive target ONLY from explicit text in $ARGUMENTS. Do NOT infer from conversation context.
Announce: Running api-contract-audit - scope: [FULL | target: <resolved>] - mode: <resolved>
Step 1 - Spec discovery
Attempt sources in this order. First hit wins.
What ships with it
1 file 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.
- 9d ago First seen · 280 lines · 78 tokens per session scan A 482c2370d445
api-contract-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 3,946 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
argot-suggest-rules
Turn a convention argot has already discovered into a scripted custom rule. Runs argot conventions, surfaces the repo's mined placement conventions (where a kind of code lives — "validation in schema files", "DB access only in migrations", "business logic in the service layer, not views") and internal-API vocabulary…
boundary-validation
This skill should be used when the user asks to "validate input", "parse request data", "handle form data", "add Zod schema", "sanitize user input", or creates API endpoints and system boundaries. Provides parse-don't-validate patterns with schema validation for type-safe boundary enforcement and hostile input defense.
consistency
This skill should be used when reviewing code for naming convention violations, pattern deviations, or inconsistent API styles.
documentation
This skill should be used when reviewing for documentation drift, missing API docs, or stale comments.
java
This skill should be used when the user works with Java files (.java), asks about "records", "sealed classes", "Optional", "streams", "composition over inheritance", or discusses modern Java patterns and API design. Provides patterns for type system usage, error handling, immutability, and concurrency.
patterns
This skill should be used when the user asks to "create an API endpoint", "add CRUD operations", "implement event handlers", "set up logging", "add configuration", or builds features involving database operations, REST/GraphQL APIs, pub/sub patterns, or service configuration. Provides implementation patterns that…