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 skills add saeedkolivand/ai-job-hunter-app --skill deployment-rulesgit clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/deployment-rules)<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/deployment-rules"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/deployment-rules/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/saeedkolivand/ai-job-hunter-app/deployment-rules"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/deployment-rules.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 | $0.00049 | $0.00726 |
| Opus 5 | $0.00024 | $0.00363 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
deployment-rules 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 7d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment / release rules
Releases run only on manual dispatch (Actions → "🚀 Release" → action: release); semantic-release then derives the bump + notes + tag. Nothing auto-runs on push to main; never manually tag or bump versions.
Release triggers (commit type → bump)
feat:→ minor ·fix:/perf:→ patch ·BREAKING CHANGEfooter → minor (0.x guard —release.config.mjsmaps breaking→minor while pre-1.0).refactor:/docs:/chore:/ci:/test:→ no release.
Commit messages (commitlint, blocks the commit)
- Subject lower-case, ≤100 chars, imperative, no trailing period (acronyms like URL/API/DOCX must be lowercased or reworded).
- Body lines ≤200; blank line between subject and body.
- Type ∈
feat|fix|perf|refactor|ui|style|test|docs|build|ci|chore|revert.
Version sync
Version files are synced by scripts/sync-tauri-version.cjs — don't hand-edit them; a mismatch breaks the release (CRITICAL).
Updater
Updater manifest (latest.json) + signing key integrity — a broken/unsigned update is CRITICAL (defer the security lens to tauri-security-reviewer).
Pre-push
Trust the pre-push hook; investigate failures rather than --no-verify.
External standards & best-practices (verified 2026-06-19)
- Conventional Commits 1.0.0 —
type(scope)!: description;feat→MINOR,fix/perf→PATCH,!/BREAKING CHANGE:→MAJOR in the generic spec (this repo overrides breaking→MINOR while on0.x— see Release triggers above). https://www.conventionalcommits.org/en/v1.0.0/ - SemVer 2.0.0 —
MAJOR.MINOR.PATCH; pre-release-rc.1/ build+meta. https://semver.org/spec/v2.0.0.html - semantic-release (v24+) — derives bump + notes + tag from commit types; never hand-tag/hand-bump; sync version files via the tool, not by hand. https://github.com/semantic-release/semantic-release
- Keep a Changelog 2.0.0 (released 2026-06-07 — format unchanged from 1.1.0: newest-first,
YYYY-MM-DD,Unreleased+[YANKED], six types Added/Changed/Deprecated/Removed/Fixed/Security; only guidance restructured). https://keepachangelog.com/
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.
- 7d ago First seen · 41 lines · 49 tokens per session scan A 52380c93b64e
deployment-rules is a skill published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 726 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
deployment-procedures
Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.