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/procedure-promotenpx skills add yarlson/yarstack --skill procedure-promotegit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/procedure-promote)<a href="https://agentmods.dev/skills/yarlson/yarstack/procedure-promote"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/procedure-promote.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 | $0.00061 | $0.00487 |
| Opus 5 | $0.00030 | $0.00244 |
| Sonnet 5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
procedure-promote 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote a Procedure
Turn proven know-how into a reusable procedure without modifying installed plugin content or activating unreviewed instructions.
Qualification
Promote a candidate only when the user explicitly requests it or at least two independent episodes show the same successful procedure. The steps must be stable, prerequisites identifiable, and success verifiable.
Reject project facts, one-off fixes with unknown causes, behavioral policy that belongs in agent instructions, and procedures whose safe scope cannot be stated. Leave an ineligible candidate unchanged and report it as deferred. An explicit promotion request does not waive these evidence and safety checks.
Workflow
- Read the candidate and every supporting episode. Confirm the evidence shows success rather than a proposed or partially completed approach.
- Search the vault's skills/ tree and the user's configured Agent Skill directories for the same trigger and outcome.
- Draft either a new skill or a focused patch to an existing skill under inbox/skills/. Do not create a near-duplicate. If the current request does not authorize a vault write, show the draft without storing it.
- Use lowercase kebab-case and frontmatter containing exactly name and description. The description must state both what the skill does and when it applies.
- Include prerequisites, ordered steps, verification, meaningful failure modes, safety and authority boundaries, and a Provenance section naming the source episodes and last successful verification.
- Show the complete proposal. Promote it to the vault's skills//SKILL.md or another user-approved skill directory only after explicit approval.
- Validate the promoted skill with the target agent's native validator when available. Do not claim it is active until the target agent can discover it.
Do not patch a skill based on name alone. If distinct procedures would use the same name, choose an unambiguous trigger-based name or stop for the user's decision; never overwrite the existing skill.
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.
- 4d ago First seen · 48 lines · 61 tokens per session scan A d4ac1fdf4441
procedure-promote is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 7d ago), licensed MIT. It adds 61 tokens to every session and 487 once invoked, about $0.0003 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…
audit-plan-implementation
Independently audit a task attempt or completed run against a frozen plan, checking ownership, evidence, acceptance, and final readiness.
agent-first-planning
Create or revise production-ready SDD plans for agent execution, including clarification, specification, freeze inputs, ownership, budgets, and evidence contracts.
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…