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/gitguardian/ggmcp/docker-image-tagsnpx skills add GitGuardian/ggmcp --skill docker-image-tagsgit clone --depth 1 https://github.com/GitGuardian/ggmcpWrote 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/gitguardian/ggmcp/docker-image-tags)<a href="https://agentmods.dev/skills/gitguardian/ggmcp/docker-image-tags"><img src="https://agentmods.dev/badge/skills/gitguardian/ggmcp/docker-image-tags.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00604 |
| Opus 5 | $0.00028 | $0.00302 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
docker-image-tags 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 5d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releases and Docker image tags
Releases are release-please-driven: a release-please job in
.github/workflows/release.yml maintains a rolling chore(main): release X.Y.Z PR from conventional commits (version bumps in pyproject.toml,
server.json, and uv.lock, plus CHANGELOG.md — config in
release-please-config.json / .release-please-manifest.json). Merging
that PR is the release: the job creates the vX.Y.Z tag and a draft GitHub
release, builds and signs the image, then publishes the release only after the
image succeeds. CI never pushes commits to main outside the release PR.
Tag matrix and semantics
PUBLISHING.md ("Docker image tag matrix") is canonical for what each event
pushes, what each tag means, and the tag format contract that fixes the shape of
main-<sha>-<seq>. Read it before changing how any tag is built. Short answer to
"which tag do I deploy": X.Y.Z for prod, main-<sha>-<seq> for envs tracking
tip-of-main, never main or latest.
Gotchas
- To release: merge the open release-please PR. Never run
cz bumpor edit version numbers by hand — only release-please writes versions (.release-please-manifest.json+ git tags are canonical). - Tags created in CI with
GITHUB_TOKENdo not trigger workflows: the Docker build must stay in the same workflow run as therelease-pleasejob (aneeds:dependency), never behind anon: push: tagstrigger. - CI checks do not run on the release PR itself (it's created with
GITHUB_TOKEN) — its diff is only version/changelog files. - release-please creates normal releases as drafts; the
create-github-releasejob publishes them only after the image succeeds. It also creates releases for human-pushed escape-hatch tags. It must stay gated on a release tag existing: no-release main pushes still build themainimages and would otherwise try to publish with an empty tag name. - Never tag images with versions that outrank semver releases (e.g. a
CalVer-looking
2026.6.0): downstream semver tracking would consider every real0.x.yrelease "older" and stop proposing updates.
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.
- 5d ago First seen · 43 lines · 55 tokens per session scan A c95daea50c0f
docker-image-tags is a skill published in the GitHub repository GitGuardian/ggmcp (37 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 604 once invoked, about $0.0003 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
portainer-mcp-release
How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and…
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, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
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, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…
release-checklist
Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application boot time, then produces a pass/warn/fail report with a concrete remediation plan. Invoked with /release-checklist [git-ref-range]. Built to…
helm-update
Apply helm chart updates for Bifrost. Detects config.schema.json changes since the last helm release, applies user-requested changes, updates values.yaml / values.schema.json / helpers.tpl, bumps Chart.yaml version, updates helm README (Latest Version + Upcoming section), creates a docs MDX changelog, and updates…