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.
npx agentmods add skills/iampantherr/securecontext/publish-github-releasenpx skills add iampantherr/SecureContext --skill publish-github-releasegit clone --depth 1 https://github.com/iampantherr/SecureContextWhat 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 | $0.00099 | $0.01669 |
| Opus 5 | $0.00049 | $0.00834 |
| Sonnet 5 | $0.00020 | $0.00334 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
publish-github-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 2d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish a GitHub release
Generic procedure for shipping a new version of a project. Reads
project-specific config from <project>/.publish-github-release-config.json
if present (see references/config-schema.md).
When to use
Trigger phrases (literal words the user might type):
- "ship v1.2.3"
- "release"
- "tag a new version"
- "publish"
- "cut a release"
- "make a new release"
- "bump version and release"
- "deploy this release to github"
Auto-detect trigger: if CHANGELOG.md has a ## [Unreleased] heading with
entries underneath, and the agent has just finished a coherent unit of work,
suggest invoking this skill.
DO NOT use this for:
- Patch increments without code changes (use
npm version patchdirectly). - Pre-release / RC builds (use the
prerelease-tagskill instead — coming in a later release). - Repos with no GitHub remote (the skill assumes
ghCLI auth and a remote namedoriginpointing at GitHub).
Procedure
Step 1 — Preflight gates
Run scripts/preflight.py. Reads project config; fails fast on:
- Working tree dirty (uncommitted changes)
- Branch is not on
main(or whateverconfig.main_branchsays) - Local is behind remote on main (would force-push)
- CI is currently red on the head commit
package.jsonversion doesn't match the previous CHANGELOG entry header
Exits 0 = ready to release. Non-zero = stop and surface the failure to the operator.
Step 2 — Bump version everywhere
Run python scripts/bump-version.py --kind {major|minor|patch} (or
--version 1.2.3 for an explicit version). Reads
config.version_files and atomically rewrites the version string in
each. Default version-bearing files:
package.json(.version)- Plus anything listed in
<project>/.publish-github-release-config.json'sversion_files. SecureContext for example lists[package.json, src/config.ts, .claude-plugin/plugin.json].
Refuses to bump if the new version is already a tag.
Step 3 — Regenerate the CHANGELOG entry
What ships with it
6 files 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.
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.
- 2d ago First seen · 171 lines · 99 tokens per session scan A 0771028ae22e
publish-github-release is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 1,669 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
deploy
Use when ready to ship — runs pre-push gates (lint, typecheck, build, tests, security sweep), commits, releases, and pushes. Standalone, never auto-invoked. Push always requires explicit confirmation. Trigger with /hyperflow:deploy, "ship it", "ready to push", "release", "cut a release", "deploy".
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.
code-review-github
GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge.
clawmem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring, and memory lifecycle (pin/snooze/forget). Use when tuning retrieval, troubleshooting recall quality, or any ClawMem…
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.