Code Index MCP is a Model Context Protocol server that indexes code repositories so language models can search, examine, and navigate their contents. It supports tasks such as code review, refactoring, documentation, debugging, and architecture analysis. The catalogue skills help coding agents use the server's repository analysis workflow.
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/johnhuang316/code-index-mcp/release-prepnpx skills add johnhuang316/code-index-mcp --skill release-prepgit clone --depth 1 https://github.com/johnhuang316/code-index-mcpWrote 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/johnhuang316/code-index-mcp/release-prep)<a href="https://agentmods.dev/skills/johnhuang316/code-index-mcp/release-prep"><img src="https://agentmods.dev/badge/skills/johnhuang316/code-index-mcp/release-prep.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 | $0.00034 | $0.00586 |
| Opus 5 | $0.00017 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
release-prep 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Prep
Overview
Prepare code-index-mcp releases from a verified commit with an explicit version and release target. The reference checklist owns exact commands; this file owns the decision points and safety gates.
When to Use
- Implementation is complete and ready for a versioned release.
- The user requests a semver recommendation, version bump, release notes, tag, or GitHub release.
- A release candidate needs a final repository and test check.
Do not use during ordinary implementation or when the user has excluded release work.
Required Gates
- Stop on a dirty working tree or an unintended branch.
- Confirm the target version and release branch with the user before editing.
- Confirm release notes before creating a tag or GitHub release.
- Treat pushes, tags, package publication, and GitHub releases as separate external actions requiring user authorization.
Workflow
- From the repository root, run
uv run python .agents/skills/release-prep/scripts/run_release_checks.py; resolve every failed precondition. - Review changes since the latest
v*tag and recommend:patch: bug fixes or user-visible corrections without new surface areaminor: backward-compatible features or capability expansionsmajor: breaking API/behavior changes or migration-required releases
- After confirmation, run the full test suite using the checklist command.
- Update all four release artifacts:
pyproject.toml,src/code_index_mcp/__init__.py,.well-known/mcp.llmfeed.json, anduv.lock. Regenerateuv.lock; never hand-edit it. - Review a release-only diff and rerun the preflight checks.
- Commit with
chore(release): vX.Y.Z. - Draft user-facing release notes and obtain confirmation.
- Only when authorized, create the annotated tag, push the branch and tag, and create the GitHub release.
- Verify the remote tag, release, and related CI or publication jobs.
Resources
| Resource | Use |
|---|---|
scripts/run_release_checks.py |
Check repository state, latest tag, and version files; invoke it with the command above. |
references/release_checklist.md |
Follow the exact commands and file checklist, resolving paths relative to this skill directory. |
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.
- 5d ago First seen · 66 lines · 34 tokens per session scan A 5b74ae041050
release-prep is a skill published in the GitHub repository johnhuang316/code-index-mcp (1,005 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 586 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 2026-08-30.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…