Borrowing it
Nothing to install: this file belongs to MRNAQA/sourceweave-web-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MRNAQA/sourceweave-web-search/main/.agents/skills/sourceweave-publishing/SKILL.mdgit clone --depth 1 https://github.com/MRNAQA/sourceweave-web-searchWrote 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/mrnaqa/sourceweave-web-search/sourceweave-publishing)<a href="https://agentmods.dev/skills/mrnaqa/sourceweave-web-search/sourceweave-publishing"><img src="https://agentmods.dev/badge/skills/mrnaqa/sourceweave-web-search/sourceweave-publishing/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/mrnaqa/sourceweave-web-search/sourceweave-publishing"><img src="https://agentmods.dev/badge/skills/mrnaqa/sourceweave-web-search/sourceweave-publishing.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 | $0.00119 | $0.02826 |
| Opus 5.5 | $0.00048 | $0.01130 |
| Sonnet 5.5 | $0.00024 | $0.00565 |
| Haiku 4.5 | $0.00012 | $0.00283 |
Grade A, and why
sourceweave-publishing 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 2mo 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SourceWeave Publishing
This skill is for publishing sourceweave-web-search autonomously and safely.
The repo already has a concrete release shape. Do not invent a new one unless the user explicitly asks. The core job is to make release metadata consistent, verify the release surface, publish the package/container artifacts, and only then publish MCP Registry metadata.
Apply KISS/YAGNI/DRY/SOLID when reviewing or editing release flow:
- do not add new knobs or alternate publish paths unless the repo already uses them
- do not duplicate release logic across docs, scripts, and skill text when one source of truth already exists
- prefer small repairs to the existing workflow over new helper scripts
- stop and ask only when a real release blocker exists, not for routine operational steps
Goal
Publish SourceWeave with least surprising flow:
- bump the version in
pyproject.toml - update
CHANGELOG.mdso released changes move out ofUnreleased - review public docs and refresh
README.mdif release changes user-facing behavior - sync derived release metadata
- verify package, artifact, tests, and container surface
- commit and push release-ready state to target branch
- run GitHub release workflow
- confirm PyPI and container artifacts are live
- publish
server.jsonto MCP Registry
Source Of Truth
Treat pyproject.toml as the release version source of truth.
Use this as the canonical release-metadata sync command:
uv run python scripts/sync_release_metadata.py
The packaged script entry point is an equivalent alternative when that is more convenient:
uv run sourceweave-sync-release-metadata
The sync/check path covers:
src/sourceweave_web_search/tool.pyheader versionserver.jsonversion and package versions- Dockerfile OCI version label
docker-compose.ymlpublishable image tag
Do not hand-edit those version fields unless the user explicitly asks for a one-off repair.
The sync script does not cover every literal version occurrence in repo.
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.
- 2mo ago First seen · 383 lines · 119 tokens per session scan A 2a7d96e43b7b
sourceweave-publishing is a skill published in the GitHub repository MRNAQA/sourceweave-web-search (2 stars, last pushed 6mo ago), licensed MIT. It adds 119 tokens to every session and 2,826 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
deploy-akashic
A deployment procedure for an Akashic project that checks and merges an approved pull request, then submits the resulting code revision to update a Docker-based service. The host system handles stopping, moving, and restarting the service.
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
release-prep
Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.