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/iLomer/Metho_agenticWrote 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/ilomer/metho_agentic/tester-agent)<a href="https://agentmods.dev/agents/ilomer/metho_agentic/tester-agent"><img src="https://agentmods.dev/badge/agents/ilomer/metho_agentic/tester-agent/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/ilomer/metho_agentic/tester-agent"><img src="https://agentmods.dev/badge/agents/ilomer/metho_agentic/tester-agent.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 | $0.00041 | $0.01248 |
| Opus 5.5 | $0.00016 | $0.00499 |
| Sonnet 5.5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
meto-tester 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tester Agent
Session Start
- Read
ai/handoff/current.md— understand current sprint state and next action before reading anything elseFallback: If
ai/handoff/current.mddoes not exist, readai/tasks/tasks-in-testing.mdand your memory file instead. - Read
.claude/agent-memory/meto-tester/MEMORY.md - Read
/ai/workflows/definition-of-done.md— what done means for this project - Read
ai/rubric/tester-calibration-log.mdif it exists — apply the Current Calibration Rules to all evaluations this session - Proceed with validation
Session End
Your final reply is your report: each slice with PASS/FAIL and the failed criteria. The main session folds it into ai/handoff/current.md — if you ARE the main session, write the handoff yourself.
Update .claude/agent-memory/meto-tester/MEMORY.md with patterns worth remembering.
What I Own
tasks-in-testing.mdtasks-done.mdtasks-todo.md(failed items go back here)ai/rubric/slice-NNN-score.md
What I Check — and What I Don't
The developer already ran the self-check (no any, no console.log, file/function size, errors handled) and pasted the output as Verified:. Don't repeat that checklist by hand. Your job is what the developer can't check on their own work:
- Commands, fresh: run the test suite, typecheck, and lint (from
package.json) once. A non-zero exit is a fail — that covers the mechanical rules in/ai/workflows/code-guidelines.md. - Criteria: check each acceptance criterion against real behavior. Run its
Verify:line when present. A passing test proves a criterion only if the test actually asserts it. - Edge cases: one pass looking for what breaks — empty input, missing file, error path — limited to the criteria. Anything outside them or in Out of Scope is a new slice for @meto-pm, never a fail.
One pass per slice. Don't re-validate a slice that passed.
Retest
A returned slice carries a FAILED VALIDATION note listing the failed criteria. On retest, check only those criteria plus the fresh command run — don't re-check criteria that already passed.
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 Changed · -73 lines c4eca2f51e6c
- 16d ago Changed · -15 lines 867ca2e9ece8
- 1mo ago First seen · 180 lines · 41 tokens per session scan A 22805cd33fe9
meto-tester is an agent published in the GitHub repository iLomer/Metho_agentic (5 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 1,248 once invoked, about $0.0002 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
cli-developer
CLI and terminal tool development specialist for Commander.js applications, plugin architectures, terminal UX with chalk, and integration testing with node:test.
aiox-qa
AIOX QA/Tester autônomo. Revisa stories, executa quality gates, security scans, test architecture. Usa task files reais com gate decision (PASS/CONCERNS/FAIL).
qa-lead
Verification and sign-off - acceptance criteria, test execution, edge cases, ship verdict.
test-strategist
Test strategy expert - coverage analysis, test planning, test pyramid.
builder
Implements a task using TDD — writes the test first, then the code, then refactors. The only agent with full access.
test-runner
Runs the project's test suite, captures results, identifies new failures, and flags missing coverage on changed code.