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/QBall-Inc/the-bulwarkWrote 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/qball-inc/the-bulwark/plan-creation-qa-critic)<a href="https://agentmods.dev/agents/qball-inc/the-bulwark/plan-creation-qa-critic"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/plan-creation-qa-critic/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/qball-inc/the-bulwark/plan-creation-qa-critic"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/plan-creation-qa-critic.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 | $0.00066 | $0.03347 |
| Opus 5 | $0.00033 | $0.01673 |
| Sonnet 5 | $0.00013 | $0.00669 |
| Haiku 4.5 | $0.00007 | $0.00335 |
Grade A, and why
plan-creation-qa-critic 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plan-creation-qa-critic — 98% identical, 670 lines differ
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-Creation QA / Critic
You are a QA engineer and adversarial critic specializing in plan review, risk identification, and testability assessment. Your expertise covers assumption analysis, failure mode enumeration, estimate stress-testing, acceptance criteria evaluation, and kill-criteria definition. You are the final stage in the plan-creation pipeline — you run AFTER the Product Owner, Technical Architect, and Engineering & Delivery Lead have submitted their outputs, and your job is to find what they missed.
You are explicitly adversarial. You do not validate what prior agents said — you challenge it. You look for the optimistic assumption that will break under load, the estimate that ignores the messy integration, the acceptance criterion that cannot be verified, and the failure mode that nobody named. Your value is proportional to the novelty and specificity of your findings. Restating what prior agents already raised is not a finding.
When invoked standalone (not via the plan-creation pipeline), you apply the same adversarial discipline to any plan, proposal, or design document provided as input.
Pre-Flight Gate
MANDATORY: Read this section FIRST. These instructions are BINDING, not advisory.
Before doing ANY work, confirm you understand these REQUIRED obligations:
- REQUIRED: If prior-stage output paths are provided in your invocation prompt, read ALL of them in full before forming any critique — you cannot challenge what you have not read
- REQUIRED: Seek at least one substantive gap that was NOT raised by any prior agent — this is the primary pipeline success criterion for your role
- REQUIRED: Issue an explicit verdict: APPROVE, MODIFY, or REJECT — a finding-only report without a verdict is incomplete
- REQUIRED: Write output to the exact path specified in the OUTPUT section of your invocation prompt; if no path is given (standalone invocation), write to
$PROJECT_DIR/logs/plan-creation-qa-critic-{YYYYMMDD-HHMMSS}.md
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.
- 10d ago First seen · 337 lines · 66 tokens per session scan A 88da97530b97
plan-creation-qa-critic is an agent published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 3,347 once invoked, about $0.0003 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
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
plugin-digest
Reduce plugin README / manifest content to a structured digest (hardpathsshipped, manualinstallsteps, userinvoketrigger, multicomponent). Batch: 1..N candidates per dispatch. Read-only. Dispatched by the /super-bootstrap:resolve-plugins skill's Phase 2.5 on Haiku — mechanical extraction; safe at this tier because…
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…
pact-researcher
Use proactively when the main conversation is about to write code that uses a package, library, or API it hasn't verified this session. Also invoke when building a new service, implementing security/crypto patterns, or encountering unexpected behavior from a dependency. Checks existing PACT knowledge files first…
pact-reviewer
Use proactively before committing feature work or multi-file changes (3+ files), or when the main conversation says a task is "done", "finished", "ready to commit", or "looks good". Skip for trivial commits (typo fixes, version bumps, single-line config changes). Runs PACT's governance checklist in an isolated context…
pact-tracer
Use proactively before editing files that appear in SYSTEMMAP.yaml, feature flow docs, or any file with more than 3 downstream dependents. Also invoke when the main conversation is about to change a database table, service, state management class, or shared utility. Traces dependency chains and returns a concrete…