Borrowing it
Nothing to install: this file belongs to tbhb/vale-ai-tells. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tbhb/vale-ai-tells/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/tbhb/vale-ai-tellsWrote 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.
[](https://agentmods.dev/skills/tbhb/vale-ai-tells/release)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/release"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/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.
<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/release"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 19 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00913 |
| Opus 5 | $0.00036 | $0.00456 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00091 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Perform a full release for version $ARGUMENTS.
1. Pre-flight
- Run
git status. Working directory must show no changes and stay onmain. - Run
git log --oneline -3. Confirm the tip commit matches what you want tagged. - Check version format: must match
vMAJOR.MINOR.PATCH - Get the previous version tag for use in step 4:
git tag --sort=-version:refname | grep "^v" | head -1
2. Update CHANGELOG.md
Read CHANGELOG.md and make these edits:
- Replace
## [Unreleased]with## [$ARGUMENTS_NO_V] - YYYY-MM-DD, using today's date. The heading uses the version without the leadingvto match the existing convention and to match the link reference added in step 3 (rumdl will reportMD053 Unused link/image referenceif the two get out of sync). - Insert a new empty
## [Unreleased]section before it - Add a comparison link at the bottom of the file, before the current top link:
[$ARGUMENTS_NO_V]: https://github.com/tbhb/vale-ai-tells/compare/PREV_TAG...$ARGUMENTSwhere PREV_TAG refers to the tag found in step 1 and ARGUMENTS_NO_V strips the leadingv
Writing CHANGELOG entries: Metacommentary uses scope: raw, which bypasses <!-- vale off --> inline suppression. Don't quote literal trigger phrases from that rule (the Let's [verb] patterns) in the CHANGELOG. Paraphrase them instead, as in v1.4.0.
3. Update README.md
The release workflow builds three packages at every tag (ai-tells.zip, ai-tells-commits.zip, ai-tells-experimental.zip). Bump the version in every releases/download/vX.Y.Z/... URL in the README so all package references point at the new tag.
Use grep -n "releases/download" README.md to enumerate every occurrence before editing.
4. Pre-commit checks
Run:
mise run repotools:lint-yaml: confirm any new YAML files passmise run test-clean: confirm false positives file remains clean
5. Commit
Invoke the commit skill, telling it to stage CHANGELOG.md and README.md and nothing else, and to use chore: release $ARGUMENTS as the subject. That skill owns the COMMIT_AGENTMSG draft, the Assisted-by and Signed-off-by trailers the commit-trailers hook requires, and the gates. A hand-written git commit here fails that hook, since a bare subject carries no trailers.
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.
- 10d ago First seen · 69 lines · 73 tokens per session scan A 127e700e6444
release is a skill published in the GitHub repository tbhb/vale-ai-tells (91 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 913 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.
Other skills, from other repositories
anti-slop
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
kill-slop
Audit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with in-voice swaps, then apply approved fixes. Use when the user says "kill slop", "/kill-slop [file]", "find the slop in this", "audit this for slop", or wants a deck, article, page, or draft cleaned to sound like…
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
release-jetbrains
Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.