locus-release

locus-release is a skill for Claude Code, Codex from Nano-Nimbus/locus. It costs 35 tokens per session (1,610 once invoked), scanned C, original, MIT.

A post-release checking skill for the locus project, run after a version is tagged and pushed. It checks tests, version references in documents, and benchmark charts for consistency.

In plain words
What is it for?
Running the unit-test suite, checking that documentation uses the current version, and keeping release benchmark charts up to date.
Why use it?
It catches stale release information and test regressions after shipping a new version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/bench-mcp.py --json-out /tmp/bench-mcp-results.json.

Good fit Running the unit-test suite, checking that documentation uses the current version, and keeping release benchmark charts up to date.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Nano-Nimbus/locus
agentmods
npx agentmods add skills/nano-nimbus/locus/locus-release

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for locus-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-release/github.svg)](https://agentmods.dev/skills/nano-nimbus/locus/locus-release)
Your own site
<a href="https://agentmods.dev/skills/nano-nimbus/locus/locus-release"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-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.

agentmods 80×15 button for locus-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/nano-nimbus/locus/locus-release"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,610 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01610
Opus 5 $0.00017 $0.00805
Sonnet 5 $0.00007 $0.00322
Haiku 4.5 $0.00003 $0.00161

Measured 8d ago against content hash 19fdfec9e626, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

locus-release scanned grade C with 2 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 8d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s https://pypi.org/pypi/locus-mcp/json | python3 -c "

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://pypi.org/pypi/locus-mcp/json | python3 -c "
skills/claude/locus-release/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

locus-release

Project development only. This skill operates on the locus source repository. It is not part of the palace interface and should not be invoked from within the MCP server or against a user's palace directory. End users of locus-mcp do not need this skill.

Post-release verification skill for the locus project. Run this after every version tag to catch stale version strings, prevent test regressions, and keep benchmark charts current.

When to use

  • After git tag vX.Y.Z && git push origin vX.Y.Z
  • After merging a version-bump PR
  • Whenever docs/img/ charts may be stale (benchmark scripts changed, new tools added)

Steps

1. Read pyproject.toml to get the current version

version = <value of [project].version in pyproject.toml>

2. Run unit tests — MUST NOT regress

uv run pytest tests/unit/ -q
  • If any tests fail, stop. Do not proceed until the regression is fixed.
  • Record the test count. If it decreased vs the previous release, investigate.

3. Verify version strings in docs

Check the following files contain the current version (or auto-updating badges):

File What to check
CHANGELOG.md Has an entry for ## vX.Y.Z
README.md Roadmap table includes vX.Y milestone as Complete
Dockerfile ARG LOCUS_MCP_VERSION="X.Y.Z" matches current version
pyproject.toml Source of truth — already read in Step 1

If any file is stale, update it and commit with the version bump PR (not separately).

4. Re-run MCP integration benchmark

# Write structured JSON results — avoids relying on text output format
uv run python scripts/bench-mcp.py --json-out /tmp/bench-mcp-results.json

Then verify from the JSON:

import json
r = json.load(open("/tmp/bench-mcp-results.json"))
assert r["summary"]["passed"] == 40, f"Expected 40, got {r['summary']['passed']}"
assert r["summary"]["p95_ms"] < 50, f"p95 latency regression: {r['summary']['p95_ms']}ms"

Read the full file on GitHub · 182 lines

Changes

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.

  1. 8d ago First seen · 182 lines · 35 tokens per session scan C 19fdfec9e626

Subscribe to this mod's changes

locus-release is a skill published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,610 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.