spectre: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code, Codex from joenandez/spectre. It costs 88 tokens per session (5,710 once invoked), scanned A, original, MIT.

A deployment workflow for switching Spectre between a local checkout and the public marketplace, or publishing a versioned release.

In plain words
What is it for?
Use it to activate local or public installs, or to prepare patch, minor, major, or explicitly numbered public releases.
Why use it?
It separates local testing from public publishing and checks synchronization, tests, and repository state before deployment.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is joenandez/spectre's own configuration. It tells Claude Code and Codex how to work on spectre itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spectre configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .agents/skills/verify-spectre/scripts/verify.mjs.

Reuse

Borrowing it

Nothing to install: this file belongs to joenandez/spectre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joenandez/spectre/main/.agents/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joenandez/spectre

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 release

README.md
[![agentmods](https://agentmods.dev/badge/skills/joenandez/spectre/release.svg)](https://agentmods.dev/skills/joenandez/spectre/release)
Your own site
<a href="https://agentmods.dev/skills/joenandez/spectre/release"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.05710
Opus 5 $0.00044 $0.02855
Sonnet 5 $0.00018 $0.01142
Haiku 4.5 $0.00009 $0.00571

Measured 8d ago against content hash 0a7a7449ff0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 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.

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.

.agents/skills/release/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Internal Spectre deployment workflow. Keep local deployment and public release as explicit, separate modes.

Arguments

Supported invocations:

activate local
activate public
local
public patch
public minor
public major
public X.Y.Z

Treat $ARGUMENTS as one of these forms. local is the backward-compatible alias for activate local. activate public switches installed sources but does not publish; public <version> publishes a release. If the first argument is missing or invalid, ask which mode to run. Never infer or default to a public release.

Shared Preflight

  1. Run git status --short and inspect relevant staged and unstaged diffs.

  2. Run:

    npm run sync-codex -- --quiet
    npm run sync-codex -- --check --quiet
    node .agents/skills/verify-spectre/scripts/verify.mjs
    
  3. Stop and fix any sync, test, structure, Codex, or real-CLI failure before deploying.

  4. Never stage unrelated files or use git add -A.

Persistent Local Source Activation

activate local, local, and Public Mode's pre-release deployment activate persistent user-level installs from this checkout. These commands are deployment actions, not a handoff for the user to finish.

Before changing anything, run all four inventory commands and retain their JSON for the final source report:

codex plugin marketplace list --json
codex plugin list --json
claude plugin marketplace list --json
claude plugin list --json

The local and public catalogs intentionally share marketplace name spectre and plugin identity spectre@spectre; they are alternatives, not side-by-side installs. Mutate only that exact marketplace and plugin. For Claude Code, mutate only user scope. Never remove a project/local-scope declaration; stop if one shadows the requested user source or leaves another enabled spectre@spectre install.

Codex

  1. Inspect the spectre marketplace. If absent, add this checkout. If its source is not a local path whose real path is $PWD, remove the installed plugin if present, remove only the conflicting marketplace, and add this checkout:

Read the full file on GitHub · 477 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 · 477 lines · 88 tokens per session scan A 0a7a7449ff0a

Subscribe to this mod's changes

release is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 5,710 once invoked, about $0.0004 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.