release-cutter

An automated workflow for cutting and publishing a new agnostic-ai release.

In plain words
What is it for?
Use it to prepare a release, publish its artifacts through GoReleaser, and respond if the release workflow fails.
Why use it?
It provides the required checks, versioning, changelog, commit, signed tag, push, and release-workflow steps in one process.

Agent

Install

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.

agentmods
npx agentmods add agents/chemaclass/agnostic-ai/release-cutter
Clone the repo
git clone --depth 1 https://github.com/Chemaclass/agnostic-ai
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00345
Opus 5 $0.00008 $0.00172
Sonnet 5 $0.00003 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured yesterday against content hash 8a8adcd84b31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-cutter 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 yesterday.

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.

.agnostic-ai/agents/release-cutter.md · 24 lines

What it actually says

You cut a new release of agnostic-ai.

Steps:

  1. Confirm the working tree is clean and on main. Pull the latest.
  2. Run make preflight (fmt-check + vet + lint + test). Refuse to proceed on any failure.
  3. Decide the next version per semver. Patch for fixes, minor for additive features, major for breaking changes.
  4. Drop empty ### subsections from ## [Unreleased] in CHANGELOG.md, then move the remaining lines into a new dated ## vX.Y.Z - YYYY-MM-DD section (no brackets). The released section must never carry a ### heading with no entries. Reset ## [Unreleased] to empty.
  5. Bump version in cmd/agnostic-ai/main.go.
  6. Commit chore(release): vX.Y.Z, GPG-signed.
  7. Tag with git tag -s vX.Y.Z -m "vX.Y.Z" so GoReleaser picks it up.
  8. Push branch and tag. GoReleaser builds artifacts and publishes the GitHub Release; release notes come from the matching CHANGELOG.md section.
  9. Wait for the workflow. If it fails, fix the root cause. Do not delete and retag without a clear reason.

Never skip the changelog step. The release notes pipeline reads the latest dated section from CHANGELOG.md.

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. yesterday First seen · 24 lines · 15 tokens per session scan A 8a8adcd84b31

Subscribe to this mod's changes

release-cutter is an agent published in the GitHub repository Chemaclass/agnostic-ai (11 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 345 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

tldrcrew-investigator

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.

0p9b/TLDR · 60 tokens

gpd-executor

Default writable implementation agent for bounded GPD research execution. Handles PLAN.md files or scoped tasks with checkpointing, deviation handling, state updates, and physics discipline. Spawned by execute-phase, quick, and parameter-sweep workflows.

psi-oss/get-physics-done · 51 tokens

gpd-paper-writer

Drafts and revises physics paper sections from research results with proper LaTeX, equations, and citations. Spawned by the write-paper and respond-to-referees workflows.

psi-oss/get-physics-done · 42 tokens

gpd-referee

Acts as the final adjudicating referee for staged manuscript review and performs direct manuscript or milestone review only when the invoking workflow explicitly assigns that mode. Writes REFEREE-REPORT{roundsuffix}.md/.tex, review decision artifacts, and CONSISTENCY-REPORT.md when applicable.

psi-oss/get-physics-done · 61 tokens

gpd-verifier

Verifies phase goals with direct physics checks, decisive comparisons, and a canonical VERIFICATION.md report.

psi-oss/get-physics-done · 25 tokens

gpd-experiment-designer

Designs numerical experiments, parameter sweeps, convergence studies, and statistical analysis pipelines for physics computations.

psi-oss/get-physics-done · 26 tokens