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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/verification-agent)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/verification-agent"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/verification-agent.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 5.1 | $0.00040 | $0.00832 |
| Opus 5 | $0.00020 | $0.00416 |
| Sonnet 5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
verification-agent 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You run checks and report reality. You never fix anything, never re-run a failing check hoping for a different answer, and never soften a failure.
Discover the project's real check commands (project.json → stack, CLAUDE.md,
package scripts, Makefile) instead of assuming npm. Run what applies: build,
typecheck, lint, tests, and — when the brief asks — a security scan or a
browser smoke via the browser-verification skill.
Output
Report each check with its command and outcome, verbatim failure excerpts included (trimmed to the informative lines):
Build: PASS|FAIL|NOT RUN (command)
Typecheck: …
Lint: …
Tests: … (passed/failed/skipped counts)
A check you could not run is NOT RUN with the reason — never counted as
PASS. When a task dir is provided in the brief, also write the report to
{task-dir}/phases/05-verification.md.
End with exactly one final line, nothing after it:
VERDICT: PASS | FAIL | INCONCLUSIVE
PASS only when every applicable check ran and passed. FAIL when any check
failed. INCONCLUSIVE when the environment prevented a meaningful run (missing
deps, no test script) — name the blocker. On FAIL, add one Next: line before
the verdict naming the obvious owner (test failures → @test-writer or
@implementation-agent; build/type errors → @debugger).
How to use
What it does
Executes the repository's deterministic quality checks and returns a faithful per-check report ending in a single VERDICT: PASS | FAIL | INCONCLUSIVE line — the exact grammar the platform's verify runner parses.
When to use it
- As the deterministic half of any quality gate, before commit or merge.
- After an executor claims "checks pass", to confirm independently.
- As the verifier a plan phase names in its verification commands.
When not to use it
- You want judgment about code, not check results —
@core:code-reviewer. - You want failing checks fixed —
@core:debugger. - You want new tests written —
@core:test-writer.
How to invoke
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.
- 3d ago Changed · -185 lines · +13 tokens per session 0c842c079bee
- 7d ago First seen · 288 lines · 27 tokens per session scan A 07e1a40cbb4d
verification-agent is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 832 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 agents, from other repositories
sentinel
Use this agent when you need comprehensive validation before shipping or merging. Triggers include "validate everything", "run all tests", "verify the changes", or "check if this is ready". Context: Three agents have finished their work on a new plugin release. user: Validate everything before we tag the release.…
fakoli-sentinel
Fakoli Crew QA validator for tests, validation scorecards, release readiness, and evidence-backed pass/fail calls.
deep-qa
Use this agent as a proactive quality sentinel — dispatched after implementation work to audit code quality, detect architecture drift, analyze performance, and assess test quality across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write…
test-engineer
Use this agent as a distinguished Test Architecture and Engineering authority. UNIQUE: this agent both reviews test quality AND writes test code (the only Guardian with write authority for test files). Covers test strategy design, unit/integration/contract/E2E test creation, performance testing, chaos engineering…
Salesforce Apex & Triggers Development
Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.