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 Terminal49/API --skill agent-trustgit clone --depth 1 https://github.com/Terminal49/APIWrote 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/terminal49/api/agent-trust)<a href="https://agentmods.dev/skills/terminal49/api/agent-trust"><img src="https://agentmods.dev/badge/skills/terminal49/api/agent-trust/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/terminal49/api/agent-trust"><img src="https://agentmods.dev/badge/skills/terminal49/api/agent-trust.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 | $0.00036 | $0.00338 |
| Opus 5.5 | $0.00014 | $0.00135 |
| Sonnet 5.5 | $0.00007 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
terminal49-agent-trust 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 13d 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.
What it actually says
Terminal49 agent trust
Extend this repository through one paved path and prove the change with the same checks CI runs.
Before editing
- Read the paved path for the surface you are changing.
- Read the feature map to confirm the registered MCP tools, SDK exports, and docs routes, and to find an existing tool's source.
- Keep generated files generated. Change
docs/openapi.jsonbefore SDK types, Postman, or SDK reference output.
Verification
Run:
npm run agent-verify
Use npm run agent-verify:quick only while iterating. The full command is the
completion gate and must pass before a code change is handed off.
The verifier checks:
- feature-map, toolchain-pin, and root-config ownership rules
- Vite+ format/lint and authoritative TypeScript checks
- SDK, MCP, and CLI builds and tests
- OpenAPI generation drift in the SDK types, SDK filter reference, and MCP filter schemas
- an offline MCP initialize plus
tools/listprotocol smoke
P-Stack
Follow the repository P-Stack wiring for non-trivial investigation, implementation, verification, and lesson encoding. Model choices and reasoning budget are user-local; never commit a teammate's model slugs.
What ships with it
5 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.
- 13d ago First seen · 45 lines · 36 tokens per session scan A 84b74d4ad8e6
terminal49-agent-trust is a skill published in the GitHub repository Terminal49/API (2 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 338 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
api-documentation
API Documentation & Design (OpenAPI/Swagger): Helps write and review API documentation, generate OpenAPI/Swagger specs, design RESTful APIs, and document GraphQL schemas. Use whenever the user mentions 'API docs', 'Swagger', 'OpenAPI', 'API specification', 'API design', 'REST API', 'endpoint documentation', 'API…
api-rate-limit-handler
Implement bounded, idempotency-aware API throttling, backoff, and retry handling for 429 and transient 5xx responses.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
middlewares
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstablepipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).