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/phase-validatenpx skills add yarlson/yarstack --skill phase-validategit 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 | $0.00037 | $0.00374 |
| Opus 5 | $0.00018 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
phase-validate 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.
What it actually says
Phase Validation
Own contract validation between implementation and structural review.
Workflow
- Read the authoritative contract and applicable repository rules unconditionally.
- Enumerate each observable acceptance criterion, invariant, required progress, environmental assumption, and failure case, then map it to implementation and evidence.
- Inspect changed files, tests, failure paths, cleanup, side effects, and required checks without trusting implementation claims. Confirm that each evidence method fits the relevant input, state, ordering, and failure space.
- Invoke focused review skills only when their trigger materially applies; consume read-only findings and keep fixes under this phase's authority. Use separately authorized specialist or independent challenge passes only to broaden defect discovery, verify their claims from evidence, and never treat agreement as proof.
- Use
plan-updateorspec-updatewhen the contract is incorrect or incomplete. Do not invent behavior. - Fix only implementation gaps required by the selected contract.
- Run focused checks while correcting, then run the authoritative required command once against final content.
For every criterion report VERIFIED, NOT VERIFIED, or INCONCLUSIVE, with evidence and reasoning. Independence means fresh evidence-based conclusions, not mandatory separate-agent execution.
Do not add verification dependencies or harnesses without authority; report the expected benefit and residual risk when they are unavailable. Do not perform broad maintainability refactoring, final closeout, shipping, commits, pushes, external mutations, or unrelated cleanup. Use phase-review after validation for structural regressions.
Finish when every criterion has a supported status, scoped defects are fixed, required checks reflect final content, and blockers are explicit.
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 · 25 lines · 37 tokens per session scan A 88d918da7471
phase-validate is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 374 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.