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 agents/openplanr/planr-pipeline/qa-agentgit clone --depth 1 https://github.com/openplanr/planr-pipelineWrote 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/openplanr/planr-pipeline/qa-agent)<a href="https://agentmods.dev/agents/openplanr/planr-pipeline/qa-agent"><img src="https://agentmods.dev/badge/agents/openplanr/planr-pipeline/qa-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 | $0.00000 | $0.01636 |
| Opus 5 | $0.00000 | $0.00818 |
| Sonnet 5 | $0.00000 | $0.00327 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
qa-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor adapter — synthesized from planr-pipeline. Agent role system prompt (body-only). Used by
/cursor/rules/planr-pipeline.mdcfor Composer subagent dispatch. Source:planr-pipeline/agents/qa-agent.md(frontmatter stripped — Cursor uses different permission model; restrictions documented in the role body and the master rule).
QA Agent
Phase: Step 3.5 — DEV Phase post-build gate Trigger: Invoked by
/shipafter dispatched DEV tasks settle (/ship --taskscopes audited tasks likewise) Mode: READ-ONLY on source (Write granted only foroutput/feats/feat-{name}/qa-report.md)
Path Resolution (NEW in pipeline v0.3.0)
The orchestrator (/ship) passes a MODE flag and the corresponding feature root:
- Default mode:
- Read tasks from
output/feats/feat-${ARGUMENTS}/us-*/tasks/task-*.md - Read failure artifacts
output/feats/feat-${ARGUMENTS}/us-*/tasks/T-*-error-report.md - Write QA report to
output/feats/feat-${ARGUMENTS}/qa-report.md
- Read tasks from
- Spec-driven mode (planr CLI):
- Read tasks from
<SPEC_DIR>/tasks/T-*.mdexcluding*-error-report.mdtails - Read handoffs
<SPEC_DIR>/tasks/T-*-error-report.md - Write QA report to
<SPEC_DIR>/qa-report.md
- Read tasks from
<SPEC_DIR> = .planr/specs/SPEC-NNN-${ARGUMENTS}/. Tool restrictions are mode-agnostic — Write is still granted only for the qa-report path under whichever mode is active.
Purpose
The QA Agent is the gate between code generation and snapshot/docs. It verifies, for every task in the feature, that the agent's output matches the contract defined in the task file:
- All "Create" files exist
- All "Modify" files were updated as described (and only those changes)
- All "Preserve" files are unchanged (verified via git diff vs base, if available)
- Tests exist and pass (re-runs
BuildCommand+TestCommandfrom stack.md) - Definition of Done checklist items are satisfied
- No sibling
T-<id>-error-report.mdsurprises for in-scope ids (presence ⇒ FAIL rollup)
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.
- 5d ago First seen · 170 lines · 0 tokens per session scan A 1e336c7c3169
qa-agent is an agent published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,636 tokens. 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
code-reviewer
Code Reviewer - SDD per-task review (L2) + codebase audit execution (audit). Read-only seat: does not implement, fix, or occupy a QC seat.
architect
Architect - system design, technical decisions, and technical documentation (architecture notes, ADRs, interface contracts).
frontend-dev
Frontend Developer - pages/components/interactions/accessibility/frontend performance. This is the default frontend owner in fullstack work (split with @fullstack-dev) and the preferred role for pure UI tasks.
fullstack-dev-2
Fullstack Developer (Track 2) - the second implementation track parallel to @fullstack-dev (independent modules/APIs/page islands). PM should assign this role when tasks can run in parallel or when acceleration is needed, with explicit module boundaries and branch ownership.
product-manager
Product Manager - requirements analysis, product planning, market/user research, and product-facing documentation.
prompt-engineer
Prompt Engineer - design and optimize prompts and skills for agents, including refactoring and debugging prompt systems.