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.
git clone --depth 1 https://github.com/sequant-io/sequantnpx agentmods add skills/sequant-io/sequant/releaseWrote 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/sequant-io/sequant/release)<a href="https://agentmods.dev/skills/sequant-io/sequant/release"><img src="https://agentmods.dev/badge/skills/sequant-io/sequant/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/sequant-io/sequant/release"><img src="https://agentmods.dev/badge/skills/sequant-io/sequant/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.09368 |
| Opus 5.5 | $0.00009 | $0.03747 |
| Sonnet 5.5 | $0.00005 | $0.01874 |
| Haiku 4.5 | $0.00002 | $0.00937 |
Grade A, and why
release scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s https://registry.npmjs.org/sequant | jq '."dist-tags"'`. How it starts
The opening of the file, as written. The whole thing — 862 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local overrides (read this first). Before following any instruction below, check whether
.claude/.local/skills/release/overrides.mdexists. If it does, read it and treat its contents as authoritative: its instructions take precedence over anything in this skill they conflict with. This is the supported way to tailor/releasewithout forking it —overrides.mdlives under.claude/.local/, whichsequant updateandsyncnever overwrite.
Release Skill
Automates the full release workflow: version bump, git tag, GitHub release, and npm publish.
Usage
/release [patch|minor|major] [--prerelease <tag>] [--soaked] [--dry-run]
/release- Interactive, asks for version type/release patch- Patch release (1.3.1 → 1.3.2)/release minor- Minor release (1.3.1 → 1.4.0)/release major- Major release (1.3.1 → 2.0.0)/release minor --prerelease beta- Pre-release (1.3.1 → 1.4.0-beta.0)/release --dry-run- Preview without publishing/release --soaked- Promote an already-publishednextversion tolatest(Step 9b); refused without this flag
Pre-flight Checks
Run ALL checks before proceeding. STOP if any fails.
Git Checks
# 1. On main branch
[ "$(git branch --show-current)" = "main" ] || { echo "Not on main"; exit 1; }
# 2. Clean working tree
[ -z "$(git status --porcelain)" ] || { echo "Uncommitted changes"; exit 1; }
# 3. In sync with remote
git fetch origin
[ -z "$(git log HEAD..origin/main)" ] || { echo "Behind origin - pull first"; exit 1; }
# 4. The latest CI `push` run on main is green (red-main rule, below).
# Filter to the CI workflow: without --workflow the newest push run can be
# Scorecard or another workflow, and a red CI would read as green.
ci_run=$(gh run list --branch main --event push --workflow ci.yml --limit 1 \
--json conclusion,url --jq '.[0] | "\(.conclusion) \(.url)"')
case "$ci_run" in success*) ;; *) echo "Red main: latest CI push run is '$ci_run' - revert first (#1093)"; exit 1;; esac
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 Changed a86a9441f9ec
- 11d ago Changed 6f2f04ba0a13
- 14d ago Changed 17251aa7a0d9
- 18d ago Changed · +26 lines 065280ba5cea
- 19d ago Changed · +2 lines 011dd093a749
- 24d ago Changed · +52 lines 6c0068ff4a12
- 26d ago Changed · +15 lines d2b074fab473
- 1mo ago Changed · +16 lines fe0046956ada
- 1mo ago Changed · +2 lines 949b24651093
- 1mo ago First seen · 749 lines · 23 tokens per session scan A 13af4050d0bc
release is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 9,368 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
find
Find the local coding-agent session that wrote the uncommitted changes in a file, or in a pasted snippet of changed code or comment text, and give a one-line command that resumes it. Prefers the session that authored the change over a review session. Use when asked which session, chat, thread, or agent made an edit…
pickup
Resume work in a fresh session from the newest handoff file written by /handoff, from a named handoff file, or from an unfinished orchestration run found on a local feature branch. Checks first whether commits made after the handoff already did its task.
git-workflow
Perform requested Git actions while preserving user work. Triggers on "commit", "提交".
scenario-readiness-review
Assess whether a scenario's uncommitted changes are ready to commit by querying the git-control-tower unified review endpoint for code health signals, then reviewing the actual git changes for coherence and intent.