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/yarlson/yarstack/pr-draftnpx skills add yarlson/yarstack --skill pr-draftgit clone --depth 1 https://github.com/yarlson/yarstackWhat 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 | $0.00043 | $0.00448 |
| Opus 5 | $0.00022 | $0.00224 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
pr-draft 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 yesterday.
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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft PR
Own end-to-end draft-PR publication after implementation, validation, and review are complete.
Workflow
- Confirm shipping authority, repository rules, base branch, remotes, current branch, exact scope, and completed validation and review evidence.
- Preserve unrelated staged, unstaged, and untracked work. Stop only when safe isolation is impossible or a scoped path is sensitive or unexpectedly generated.
- Create a short branch when needed, stage explicit paths with
git add -- <paths>, and review the staged path list and diff. - Run required checks when existing evidence does not cover the exact staged content.
- Follow repository PR templates, title conventions, and required fields. Otherwise write concise evidence-based
Problem,Change,Tests, and only necessaryNotessections. - Use
text-improveon the completed title and body without changing verified facts, required template wording, or technical terms. - Use
change-cleanup-reviewon the complete staged change and proposed PR presentation. Stop and report material cleanup findings unless the parent request separately authorizes repair. After an authorized repair, restage the exact scope and rerun invalidated checks and prose improvement. - Commit using repository conventions and push with an upstream when needed.
- Open a draft PR and monitor checks for the pushed commit.
- Diagnose failures from logs. Route behavior changes through
behavior-implementandtest-design, and specialist failures through their owning workflow; verify, rerunchange-cleanup-reviewwhen corrections materially move the change, then commit and push only scoped corrections. - Stop when checks pass, the user permits cancellation, or a concrete external blocker prevents meaningful progress.
Do not rewrite history, force-push, merge, mark ready, release, weaken tests, disable validation, expose secrets, or override repository PR conventions.
Finish with the draft PR URL, commits, checks, final CI state, and blockers.
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.
- yesterday First seen · 27 lines · 43 tokens per session scan A ed6734c20fda
pr-draft is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 448 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 2026-08-31.
Other skills, from other repositories
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
release-cli
Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…
ship-mobile-app
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
verify-regression-tests
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
repository-hygiene
Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.