invokta: Skill for Codex

.agents/skills/prepare-invokta-release/SKILL.md

prepare-invokta-release is a skill for Codex from vinilana/invokta. It costs 59 tokens per session (982 once invoked), scanned A, original, MIT.

A release-preparation procedure for the Invokta software project. It creates a versioned release branch and updates release files before the release is committed.

In plain words
What is it for?
Preparing or checking an Invokta release or release candidate, including version numbers, package dependencies, changelog entries, validation, and release-branch commits.
Why use it?
It reduces the risk of publishing mismatched package versions, incomplete change notes, or an unvalidated release. It also keeps release work separate from the main development branch.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

This is vinilana/invokta's own configuration. It tells Codex how to work on invokta 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 invokta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vinilana/invokta. 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/vinilana/invokta/main/.agents/skills/prepare-invokta-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vinilana/invokta

Made for: 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 prepare-invokta-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinilana/invokta/prepare-invokta-release"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/prepare-invokta-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 10
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00059 $0.00982
Opus 5 $0.00030 $0.00491
Sonnet 5 $0.00012 $0.00196
Haiku 4.5 $0.00006 $0.00098

Measured 9d ago against content hash 6d5a9931fc43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prepare-invokta-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 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.

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/prepare-invokta-release/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare an Invokta Release

Establish the release branch

  1. Read .agents/skills/invokta-delivery/SKILL.md, docs/README.md, the release gates in docs/implementation-plan-and-acceptance-criteria.md, and the ADRs represented by the unreleased changes.
  2. Inspect the working tree, current branch, local and remote mainline refs, recent tags, CHANGELOG.md, and commits since the latest release. Preserve unrelated changes and stop if they make the release slice ambiguous.
  3. Select the next semantic version from the compatibility of the Unreleased changes and the repository's prior release policy. Request a decision when the correct increment is ambiguous.
  4. Confirm the intended mainline base. If local main and origin/main diverge, resolve the base explicitly before continuing.
  5. Create or switch to chore/release-X.Y.Z from the confirmed mainline before editing any release file. Never prepare or commit a release on main.

Synchronize release metadata

  1. Bump the root version and every public package version to X.Y.Z.
  2. Bump every exact internal @invokta/* dependency pin in public packages and examples. Update version assertions and protocol client self-identification constants that intentionally track the release.
  3. Search the repository for the previous version. Classify every match as current release metadata, historical release documentation, or an unrelated dependency before changing it.
  4. Synchronize committed example lockfiles. For unpublished Invokta packages, derive integrity values from the exact locally packed X.Y.Z artifacts; never retain old integrity hashes or invent new ones. Recheck the hashes if package contents change afterward.
  5. Move the Unreleased notes under ## [X.Y.Z] - YYYY-MM-DD, update the Unreleased comparison base, and add the release link. Preserve historical entries and write all release content in English.
  6. Refresh docs/validation-record.md only with evidence produced during this release run, including the review date, accepted ADRs, test totals, coverage, and audit count.

Read the full file on GitHub · 89 lines

Files

What ships with it

1 file 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.

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 · 89 lines · 59 tokens per session scan A 6d5a9931fc43

Subscribe to this mod's changes

prepare-invokta-release is a skill published in the GitHub repository vinilana/invokta (128 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 982 once invoked, about $0.0003 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.