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 psenger/ai-agent-skills --skill startgit clone --depth 1 https://github.com/psenger/ai-agent-skillsWrote 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/psenger/ai-agent-skills/start)<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/start"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/start.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.00996 |
| Opus 5 | $0.00077 | $0.00498 |
| Sonnet 5 | $0.00031 | $0.00199 |
| Haiku 4.5 | $0.00015 | $0.00100 |
Grade A, and why
start 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start
Begins a new piece of work. Two modes — the skill determines which applies:
- User provides an issue number, URL, or reference → EXISTING ISSUE mode
- User provides a description of what needs doing → NEW ISSUE mode
For branch naming and commit format, follow the conventions skill.
Step 0 — Auth & Identity
Check for a GitHub MCP server in available tools. If none, run:
gh auth status
If neither is available, stop: "I need the GitHub MCP server or gh CLI authenticated to continue. Run gh auth login or connect the GitHub MCP server."
Confirm identity — use mcp__github__get_me if the GitHub MCP server is available, otherwise:
gh api user --jq '"@\(.login) — \(.name)"'
Show the result and ask: "I'll be acting as @username — is that right?" Wait for confirmation before continuing.
EXISTING ISSUE Mode
Step 1 — Fetch the Issue
From the issue number or URL, fetch the issue:
gh issue view <number> --json number,title,body,labels,url
Display the issue number, title, and first few lines of the body. Ask: "Is this the right issue to work on?" Wait for confirmation.
Step 2 — Start from Main
git checkout main
git pull origin main
git status --porcelain # must be empty — abort if dirty
Step 3 — Cut the Branch
Derive the slug from the issue title: lowercase, hyphenated, 2–4 meaningful words, no stop words.
Determine branch prefix from issue labels:
buglabel →fix/enhancementorfeaturelabel →feature/- Anything else →
feature/by default
git checkout -b <prefix><issue-number>-<slug>
Example: feature/14-add-handoff-skill or fix/23-vault-scribe-toc
Report: "Branch feature/14-add-handoff-skill created from main. You're ready to work."
NEW ISSUE Mode
Step 1 — Classify the Work
From the user's description, determine: is this a feature (new capability, new skill, enhancement) or a bug (something broken, incorrect behaviour, wrong output)?
What ships with it
4 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.
- 8d ago First seen · 111 lines · 154 tokens per session scan A 26a70640a91a
start is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 996 once invoked, about $0.0008 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
ijfw-ship
Use when the user says 'ship it', 'ship this', 'release', 'publish', 'launch', 'deploy', 'go live', 'wrap this up', 'time to ship', or invokes '/ijfw-ship'. Domain-aware release — software (test → tag → push → publish), book (final edit → format → KDP / agent / Substack), campaign (review → schedule → launch →…
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.
contribute-start
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue.
workspace
Multi-repo workspace coordinator for shared team context. Initialize .adlc/ structure, configure .gitignore, discover child repos, link them as Git submodules, and audit workspace health. Use --init for first-time setup, default mode for ongoing auditing.
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".