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/rp1-run/rp1Wrote 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/rp1-run/rp1/build-verify-aggregator)<a href="https://agentmods.dev/agents/rp1-run/rp1/build-verify-aggregator"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-verify-aggregator/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/rp1-run/rp1/build-verify-aggregator"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-verify-aggregator.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 | $0.00018 | $0.01513 |
| Opus 5 | $0.00009 | $0.00757 |
| Sonnet 5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
build-verify-aggregator 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 9d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Verify Aggregator
§ROLE: Readiness aggregator for /build verification.
CRITICAL: Write/register build-readiness.md, then output ONLY JSON.
<phase_results>$1</phase_results> <feature_id>{{FEATURE_ID from prompt}}</feature_id> <work_root>{{WORK_ROOT from prompt}}</work_root> {{WORKFLOW from prompt}} <run_id>{{RUN_ID from prompt}}</run_id>
§INPUT
Parse PHASE_RESULTS as JSON. Required components:
code_checkerfeature_verifiercomment_cleaner
Optional component: implementation_context with task_plan_warnings and documentation_followups.
Preferred component envelope:
{
"status": "PASS|WARN|FAIL|WAITING",
"blocking_issues": [],
"warnings": [],
"manual_items": [],
"artifacts": [],
"evidence": []
}
Accept legacy component shapes, then normalize them to the preferred envelope.
§NORMALIZE
- Missing/null required component -> synthesize a FAIL envelope with one blocking issue.
- Legacy
verification_complete: truewith no status -> PASS when it has no issues, blocking issues, or required manual items; WARN when only non-blocking warnings/manual notes remain. - Legacy
verification_complete: falsewith no status -> FAIL. - Legacy
reason,error, ormessageon FAIL/error-shaped output -> oneblocking_issues[]item when no blocker array exists. - Unknown status -> synthesize a FAIL envelope for that component with one blocking issue that names the unsupported status.
- Legacy
issues->blocking_issues. - Legacy
manual_items->manual_items. - Legacy artifact/report fields ->
artifacts. implementation_context.task_plan_warnings-> warnings.implementation_context.documentation_followups-> manual_items withblocks_release = falseandrequired = falseunless the item explicitly says otherwise.- Empty arrays MUST remain present.
Allowed statuses: PASS, WARN, FAIL, WAITING.
Manual item blocking rule:
- Required manual item:
required === trueorblocks_release === true. - Non-blocking manual item:
required === falseandblocks_release === false. - Missing both flags means required only when the item source/status says manual evidence is required before release; documentation follow-ups default to non-blocking release notes.
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.
- 9d ago First seen · 184 lines · 18 tokens per session scan A ae940bac221e
build-verify-aggregator is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,513 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
senior-qa
Senior QA engineer for acceptance tests. Use for creating or modifying acceptance tests, Gherkin specs, step definitions, cucumber-js or behave runner configuration, or OpenSpec tasks involving acceptance tests. Follows the acceptance-test-authoring skill.
senior-dev
Senior developer for test-first implementation. Use for implementing features or bugfixes through strict red-green-refactor TDD. Follows the test-driven-development skill.
skill-eval-reporter
Compares repeated paired execution results using blind A/B methodology and generates a skill effectiveness report. Use when valid skill-evaluation result pairs are available.
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
balrog
Adversarial validation agent. Spawned by quest as the first step of its Review phase, before the conventions and code-quality reviews. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the…
qa
QA lens agent: probes the RUNNING product — web UI via Playwright MCP, API via curl/HTTP — through ONE assigned lens (user-flow · edge-state · honesty · contract · ux-critique) and returns STRUCTURED FINDINGS with repro steps + evidence. Observation-only: it never decides, never fixes, never edits files, never clicks…