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 decodingai-magazine/building-a-coding-agent-from-scratch-course --skill skills-releasegit clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-courseWrote 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/decodingai-magazine/building-a-coding-agent-from-scratch-course/skills-release)<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/skills-release"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/skills-release/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/decodingai-magazine/building-a-coding-agent-from-scratch-course/skills-release"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/skills-release.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 | $0.00047 | $0.00923 |
| Opus 5 | $0.00023 | $0.00462 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
skills-release 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 today.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skills-release — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Release
Overview
main is the distribution branch: /plugin marketplace add zenml-io/kitaru-skills
installs whatever main holds, immediately. develop is the working base. A
release moves main forward to develop's current commit as a fast-forward
and stamps a plugin version, so main is always an exact snapshot of
develop at release time.
The main-release-only ruleset blocks all pushes and PR merges to main
except by repository admins. A release is therefore an admin running this
checklist — never a PR into main, never a force push.
Versions are this repository's own plugin versions. Do not reuse Kitaru product version numbers; state tested Kitaru compatibility in the release notes instead.
Preconditions
Stop and resolve before releasing if any of these fail:
- On
developwith a clean working tree. git fetch origindone; localdevelopin sync withorigin/develop.- Fast-forward is possible:
git merge-base --is-ancestor origin/main origin/developexits 0. A non-zero exit meansmainhas commitsdeveloplacks — investigate how they got there; never force-push over them.
Steps
-
Review what ships:
git log --oneline origin/main..origin/develop. Draft release notes from these commits (what changed, why it matters to installers), plus a "Tested against Kitaru X.Y" line when known. -
Agree the next version with the user: minor for new or changed skills, patch for fixes and docs-only changes.
-
Bump all three version fields to the same value:
.claude-plugin/plugin.json→.version.claude-plugin/marketplace.json→.metadata.version.claude-plugin/marketplace.json→.plugins[0].version
-
Validate:
jq . .claude-plugin/plugin.jsonandjq . .claude-plugin/marketplace.jsonparse, and all three fields match:jq -r .version .claude-plugin/plugin.json jq -r '.metadata.version, .plugins[0].version' .claude-plugin/marketplace.json -
Commit only the two JSON files on
developwith subjectRelease vX.Y.Z, then pushdevelop. -
Tag the release commit:
git tag vX.Y.Z && git push origin vX.Y.Z. -
Fast-forward
main:git push origin develop:main. No--forceever — a rejection means the push is not a fast-forward; go back to Preconditions. -
Publish the drafted notes via a file, never inline in the command — commit subjects routinely contain backticks, which the shell would execute as command substitution inside a
--notes "..."argument. Write the notes to a scratch file with a file-writing tool (or a quoted heredoc,cat > notes.md <<'EOF'), then:
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.
- today First seen · 87 lines · 47 tokens per session scan A 3b20281fdcd7
skills-release is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (374 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 923 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
release
Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.
release-engineering
Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration gates, rollback, deployment checks, and release readiness. Use when preparing a release, shipping a risky PR, coordinating app/backend/database rollout, recovering from a bad deploy, or defining release…
dsh-plugin-publisher
A release tool for DSH plugins, where DSH is the DeepSeek Harness used to load these add-ons. It validates an existing plugin package, publishes it through npm, Git, or a tarball, and checks that the harness can load it.
lov-skill-optimizer
Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, version drift, dirty worktrees, shared…
lov-skill-publisher
Publish or submit a validated Skill. Default to the LovStudio official website, run lov-skill-pricing automatically, and use other channels only when explicitly named.
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.