release-aid

release-aid is a skill for Claude Code from AndreVianna/aid-methodology. It costs 123 tokens per session (4,129 once invoked), scanned A, original, MIT.

A release procedure for the AID methodology repository. It updates the version and release notes, runs checks, creates a tag, publishes through the required channels, and verifies the result.

In plain words
What is it for?
Use it to publish major, minor, patch, or beta releases of the AID repository.
Why use it?
It gathers the many steps of a software release into one controlled process. It pauses at points that require a person, such as merging, pushing a tag, or confirming publication.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .claude/skills/generate-profile/scripts/run_generator.py && git diff --exit-code -- profiles/ # render-drift clean.

Good fit Use it to publish major, minor, patch, or beta releases of the AID repository.

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/AndreVianna/aid-methodology
agentmods
npx agentmods add skills/andrevianna/aid-methodology/release-aid

Made for: Claude Code.

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-aid

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/release-aid"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/release-aid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00123 $0.04129
Opus 5 $0.00062 $0.02065
Sonnet 5 $0.00025 $0.00826
Haiku 4.5 $0.00012 $0.00413

Measured 9d ago against content hash 32bcafcd19e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

release-aid scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

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

- **PyPI:** `curl -s https://pypi.org/simple/aid-installer/ | grep <target-normalized>` — use
.claude/skills/release-aid/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release AID

Maintainer-only skill — outside canonical/. Like generate-profile, this lives only at .claude/skills/release-aid/ — it is NOT in canonical/skills/, is NOT rendered to profiles/, and is NEVER shipped to adopters. It operates on the AID repo itself. Edit it directly. It is a runnable procedure, not a spec — for the format/architecture of a release see .aid/knowledge/infrastructure.md; for the deep runbook (recovery, release.sh flags) see docs/release.md. This skill EXECUTES the process and closes the gap those two leave open: it always updates the release notes as part of the release.

Cuts one release of the AID repo — beta or stable — from the command to artifacts published in the right places with every check green. Runs the whole sequence autonomously, pausing only at the irreversible human-gated points: the PR merge, the tag push, and confirming the publish.


Argument — REQUIRED

/release-aid <level> where <level> is exactly one of major | minor | patch | beta.

The argument is required. If it is missing or not one of the four values, STOP and ask (one clear question) which level to release — do NOT default, guess, or proceed. Only continue once a valid level is chosen.


Step 0 — Resolve the target version

Read the current version: cat VERSION (source of truth; format M.m.p optionally -beta.N). Never trust a version hard-coded in prose. Compute the target by the level, bumping that level and zeroing every level below it:

level current is stable M.m.p current is beta M.m.p-beta.N
major (M+1).0.0 (stable) (M+1).0.0 (stable)
minor M.(m+1).0 (stable) M.(m+1).0 (stable)
patch M.m.(p+1) (stable) M.m.p (stable — PROMOTE: drop the -beta.N, do not bump)
beta M.m.(p+1)-beta.1 (start the next patch's beta line) M.m.p-beta.(N+1) (next beta of the same target)

Read the full file on GitHub · 292 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. 9d ago First seen · 292 lines · 123 tokens per session scan A 32bcafcd19e9

Subscribe to this mod's changes

release-aid is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 4,129 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.