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/membrane/api-gateway/release-notesnpx skills add membrane/api-gateway --skill release-notesgit clone --depth 1 https://github.com/membrane/api-gatewayWhat 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 | $0.00124 | $0.01639 |
| Opus 5 | $0.00062 | $0.00820 |
| Sonnet 5 | $0.00025 | $0.00328 |
| Haiku 4.5 | $0.00012 | $0.00164 |
Grade A, and why
release-notes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release notes
Produce release notes for the next Membrane release by diffing master against the last release and turning the intervening commits into a clean, grouped, PR-linked changelog — the kind that goes on the project's GitHub Releases page.
Repo: membrane/api-gateway. PR URL pattern: https://github.com/membrane/api-gateway/pull/<N>.
1. Determine the range: <base>..master
The base is the last released version. Releases are marked by a commit whose subject is
Release X.Y.Z (#PR) (immediately followed by a Snapshot version commit). The local tags
lag behind, so detect the base from these commits, not from git tag.
- If the user named a version (e.g. "since 7.2.3"), use that commit as the base:
# Note the trailing space — git uses POSIX regex, so `\b` is NOT supported here. BASE=$(git log -E --grep="^Release 7\.2\.3 " --format=%H master | head -1) - Otherwise auto-detect the most recent release:
Take its hash asgit log -E --grep="^Release [0-9]+\.[0-9]+\.[0-9]+ " --format="%H %s" master | head -1BASEand read the version from its subject.
The new version being released is the pom version minus -SNAPSHOT:
grep -m1 '<version>' pom.xml # e.g. 7.2.4-SNAPSHOT -> 7.2.4
Sanity-check the range before writing anything:
git log --oneline $BASE..master | wc -l # how many commits
git log --pretty="%s" $BASE..master # the subjects to triage
If the range is empty (master == last release), say so and stop.
2. Collect and enrich
For each commit on $BASE..master, pull the subject and the trailing PR number:
git log --pretty="%s" $BASE..master
Most subjects end in (#NNNN) — that's the PR. Turn it into a link
[#NNNN](https://github.com/membrane/api-gateway/pull/NNNN). If a subject has two trailing
numbers (e.g. ... (#2988) (#2995)), the last one is the merge PR — link that one.
Read the subject for meaning; rewrite terse or type:-prefixed subjects into a user-facing
sentence. Strip conventional-commit prefixes (feat:, fix:, chore:, build:, refactor:,
docs:) from the displayed text — they only inform which group the entry belongs in.
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.
- yesterday First seen · 121 lines · 124 tokens per session scan A 0322b80b9e27
release-notes is a skill published in the GitHub repository membrane/api-gateway (638 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 1,639 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
api-design-patterns
Design robust APIs with RESTful patterns, GraphQL schemas, versioning strategies, and error handling conventions. Supports OpenAPI/Swagger documentation and SDK generation patterns. Triggers on API design, schema definition, endpoint architecture, or developer experience requests.
api-designer
Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.
api-design
Design and implement RESTful APIs with proper routing, validation, error handling, and documentation. Use when building new API endpoints, designing API architecture, or improving existing APIs.
api-design-first
Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices, validates endpoints, handles versioning, pagination, error formatting, authentication patterns, rate limiting, and idempotency. Activates when users say "design an API", "create OpenAPI spec", "API endpoint"…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…