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/magegojo/conch/release-versionnpx skills add MageGojo/conch --skill release-versiongit clone --depth 1 https://github.com/MageGojo/conchWhat 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 | $0.00052 | $0.01374 |
| Opus 5 | $0.00026 | $0.00687 |
| Sonnet 5 | $0.00010 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
release-version 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release New Version & Draft GitHub Release
Bumps the project version across all config files, updates the CHANGELOG, pushes a tag, and creates a draft GitHub release using gh.
When to Use
- Releasing a new patch, minor, or major version of r-shell
- Creating a GitHub draft release with changelog notes
- Tagging a new version and pushing to origin
Procedure
1. Determine Bump Type
Ask (or infer from the argument) whether this is a patch, minor, or major bump:
| Type | When | Example |
|---|---|---|
patch |
Bug fixes, small tweaks | 1.2.3 → 1.2.4 |
minor |
New features, backward-compatible | 1.2.3 → 1.3.0 |
major |
Breaking changes | 1.2.3 → 2.0.0 |
2. Run the Version Bump Script
# Replace <type> with patch, minor, or major
pnpm run version:<type>
This updates all version locations atomically and creates a git commit:
package.jsoncli/Cargo.tomlcli/Cargo.lockCHANGELOG.md(adds a skeleton section)
Read the new version from package.json:
node -p "require('./package.json').version"
3. Update CHANGELOG.md
First, get the actual commits since the previous tag. Find the previous tag and list every commit:
PREV_TAG=$(git tag --sort=-v:refname | sed -n '2p') # second-newest tag
git log "${PREV_TAG}..HEAD" --oneline --no-merges
⚠️ CRITICAL — Do NOT fabricate changelog entries. Every bullet point MUST correspond to a commit in the output above. Do not copy bullets from older versions, do not invent features, and do not summarize the whole project history.
Open CHANGELOG.md and fill in the new version section that the script created. Replace the placeholder lines with actual release notes derived strictly from the commit list, grouped under:
### Added— new features (feat:commits)### Changed— modifications to existing behavior (refactor:,perf:commits)### Fixed— bug fixes (fix:commits)### Removed— anything deleted (omit section if empty)
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 · 136 lines · 52 tokens per session scan A fb0c6c1791f2
release-version is a skill published in the GitHub repository MageGojo/conch (3 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 1,374 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 2026-08-31.
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.