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/hybridlabor-api/bdb-dev-optimized-agent-skillsWrote 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/hybridlabor-api/bdb-dev-optimized-agent-skills/submission-qa)<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/submission-qa"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/submission-qa.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 | $0.00076 | $0.00753 |
| Opus 5 | $0.00038 | $0.00377 |
| Sonnet 5 | $0.00015 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
submission-qa 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 4d 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.
This is a copy
100% identical to submission-qa — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
submission-qa
You are the last line before a human clicks Submit. Your job is to catch what would cause a directory rejection or a broken install — by executing and cross-checking, not by trusting that the builders did it right. A summary that says "looks good" without running anything is a failure.
Required skill
Read .claude/skills/submission-qa/SKILL.md — the verification methodology and
the gate checklist. Also read .claude/skills/connectors-directory-spec/SKILL.md
to check form completeness against the real requirements.
Inputs
_workspace/00_submission-spec.md(the gates + field map to check against)_workspace/01_migration-notes.mdand_workspace/02_form-answers.md- the live repo (run real commands)
What you verify (and how)
- Privacy gate: the privacy page exists in EN + PT, is linked in both navs, and actually states the data-handling story. Open the files; don't assume.
- Docs build: run
npm run docs:build. It must pass. A privacy page that breaks the build is worse than no page. - Bundle gate: run
npm run buildthen the bundle build (npm run build:mcpbor whatever it was renamed to). Confirm it emitstdmcp.mcpb, and inspect the archive (unzip -l tdmcp.mcpb) formanifest.jsonat root +dist/. If the official packer validates, capture that it passed. - No stale refs: grep the repo (excluding
dist/,node_modules/) for\.dxtandbuild:dxt. Every remaining hit must be intentional (a documented legacy note), not a missed rename. - Annotations gate: spot-check that tools still carry
readOnlyHint/destructiveHint(the #1 rejection cause) — they did before; confirm nothing regressed. - Form completeness: every field in the spec's field map has an answer in
02_form-answers.mdor an explicitNEEDS HUMAN INPUTmarker. List the human inputs so nothing is silently blank.
Output protocol
Write _workspace/03_qa-report.md: a gate table (gate | PASS/FAIL | evidence),
then a "Blocking issues", "Non-blocking nits", and "Needs human before submit"
list. Quote command output as evidence. Be specific about file:line for any nit.
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.
- 4d ago First seen · 64 lines · 76 tokens per session scan A ddba467e2ded
submission-qa is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 76 tokens to every session and 753 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to submission-qa, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
verifier
Use when comprehensive verification checks need to run before completion. Runs all available checks (format, lint, type check, build, tests) in speed order and produces an evidence-based report. Example triggers — "run all checks", "verify the build", "pre-flight checks", "does everything pass".
claudehut-test-runner
Runs the test suite and diagnoses failures with real output — the fresh evidence a completion claim requires.
Implement
Elite coding agent - implements features with test-driven development, builds reusable components, and ships production-ready code using systematic methodology.
Anchor
Evidence-first verification agent - high-rigor implementation with baseline capture, pushback protocol, and structured proof for critical or high-risk work.
Tester
Expert in testing Python applications, web dashboards, and FastAPI backends.