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/codagent-ai/agent-skills/releasenpx skills add Codagent-AI/agent-skills --skill releasegit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWhat 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 | $0.00090 | $0.00680 |
| Opus 5 | $0.00045 | $0.00340 |
| Sonnet 5 | $0.00018 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a release PR by gathering merged PRs, calculating the version bump, writing changelog entries, and opening the PR.
Out of Scope
This skill does not resolve merge conflicts, create release PRs when required GitHub tooling is unavailable, or curate changelog content beyond the generated PR set. Stop and report the blocker when prerequisites fail.
Steps
1. Gather release info
Run the info script to collect merged PRs and calculate the version:
bash .agents/skills/release/scripts/release-info.sh
Capture stdout as JSON. The script writes all structured responses, including errors, to stdout. If the output contains "error", stop and report the message to the user.
2. Show the release summary
Display to the user:
- Version bump:
current_version→new_version - Number of PRs by category
- List each PR number and title, grouped by Major / Minor / Patch
3. Write changelog descriptions
For each PR in the JSON output, write a one-sentence description that is slightly more informative than the raw PR title. Strip the conventional commit prefix from the title (feat:, fix:, chore:, etc.) and expand it into a sentence that gives enough context to understand the change without clicking through.
4. Format the changelog section
Build the changelog section for the new version. Only include sections that have entries. Sort entries by PR number ascending within each section.
Format:
## <new_version>
### Major Changes
- [#<number>](https://github.com/Codagent-AI/agent-skills/pull/<number>) <description>
### Minor Changes
- [#<number>](https://github.com/Codagent-AI/agent-skills/pull/<number>) <description>
### Patch Changes
- [#<number>](https://github.com/Codagent-AI/agent-skills/pull/<number>) <description>
5. Write the changelog section to a temp file
Write the formatted changelog section (from step 4) to a temporary file:
TMPFILE=$(mktemp)
cat <<'CHANGELOG_EOF' > "$TMPFILE"
<paste the formatted changelog section here>
CHANGELOG_EOF
echo "$TMPFILE"
What ships with it
2 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.
- 2d ago First seen · 91 lines · 90 tokens per session scan A e6d80554a9b2
release is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 680 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.