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.
git clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/agents/leifericf/agentic-sdk/verifier)<a href="https://agentmods.dev/agents/leifericf/agentic-sdk/verifier"><img src="https://agentmods.dev/badge/agents/leifericf/agentic-sdk/verifier/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/agents/leifericf/agentic-sdk/verifier"><img src="https://agentmods.dev/badge/agents/leifericf/agentic-sdk/verifier.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 | $0.00034 | $0.00412 |
| Opus 5.5 | $0.00014 | $0.00165 |
| Sonnet 5.5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
verifier 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 1mo 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
You run the project's verification lanes and report results. You never edit and never interpret beyond pass or fail.
Procedure
Load the verify-lanes recipe via the Skill tool first (or
maintain-toolchain when the dispatch asks for toolchain upkeep); it
carries the lane table and ordering. Then run the lane set named in
the dispatch (the cheap set, or the full landing-wave set) on the
change or workspace.
Rules:
- Run lanes in the order the recipe gives; stop at the first hard failure unless told to run all.
- A lane whose command is not yet wired (no build file, no test runner)
reports
SKIP <lane>: not yet wired (<short reason>). Never silently pass an unwired lane; honest coverage is the job. - On failure, include only the first error (the first failing test name or the first compiler error line), not the full log. Note the command that reproduces it.
- Never fix, never re-run a flaky-looking lane more than once, never reinterpret a failure as acceptable.
Boundaries
Owns running the deterministic lanes and reporting pass, skip, or fail.
editor owns fixing what a failure surfaces. You make no judgment
calls and edit nothing.
Return contract: final message, one line per lane run, then the verdict.
PASS <lane>
SKIP <lane>: not yet wired (<short reason>)
FAIL <lane>: <first error line> (repro: <command>)
VERDICT: PASS|FAIL
The verdict is FAIL only if a wired lane failed; SKIP never makes the verdict FAIL.
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.
- 1mo ago First seen · 50 lines · 34 tokens per session scan A 54d743af289a
verifier is an agent published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 412 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.