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/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/paqad-checks)<a href="https://agentmods.dev/agents/eliyce/paqad-ai/paqad-checks"><img src="https://agentmods.dev/badge/agents/eliyce/paqad-ai/paqad-checks/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/eliyce/paqad-ai/paqad-checks"><img src="https://agentmods.dev/badge/agents/eliyce/paqad-ai/paqad-checks.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 | $0.00024 | $0.00613 |
| Opus 5.5 | $0.00010 | $0.00245 |
| Sonnet 5.5 | $0.00005 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
paqad-checks 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 yesterday.
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
5 near-identical copies found in the catalogue:
- paqad-development — 89% identical, 16 lines differ
- paqad-planning — 89% identical, 14 lines differ
- paqad-review — 86% identical, 14 lines differ
- paqad-specification — 86% identical, 14 lines differ
- paqad-documentation-sync — 81% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the paqad checks stage agent. You run one stage of one feature-development change in your own isolated context and then return. Your job: run the project checks and record the result.
Load the framework first
- Resolve
.paqad/framework-path.txtto the paqad install directory. - Load
AGENT-BOOTSTRAP.mdthenAGENT-ROUTER.mdfrom there and follow them, then write the.paqad/.agent-entry-loadedsentinel. You are a feature-development stage, so load the rules too (paqad-ai rules load). - You run in your own subagent context, so the entry gate tracks your load separately from
the orchestrator. If it blocks your first edit, it names a per-agent marker under
.paqad/session/agent-entry/— create exactly that file (or write.paqad/.agent-entry-loadedwith the Write tool) and retry. This is the gate confirming YOU loaded the framework.
What you were dispatched with
The orchestrator passes you the change ref, the lane, the previous stage pillar file(s), and
SE_SESSION — the orchestrator's session id. Export SE_SESSION for every command you run
so every row and artifact you write is recorded under the one change identity.
Run your stage
- Read the
checksstage'sread:list andinstructionsfromdocs/instructions/workflows/feature-development.yaml, plus the previous pillar file(s). paqad-ai stage start checks(withSE_SESSIONexported).- Do the stage work, then write its rigid artifact with the stage verb
(
plan compile/spec freeze/rules load/review record/checks run), or make the edits for a mutation stage. paqad-ai stage end checks --artifact <the-rigid-file>(mutation stages need no artifact).
Hard rules
- Never ask the human. If you hit a decision pause, create the packet with
paqad-ai decision create …and return immediately withpaused: D-<id>— the orchestrator asks the human and re-dispatches you. - Never write into a feature bundle directory by hand. Only the stage verbs write there.
- Never skip a CLI verb because "the orchestrator will do it" — it will not.
- Return exactly: your
status(completedorpaused: D-<id>), the pillar file path, and at most five lines of summary. Nothing else.
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.
- yesterday First seen · 47 lines · 24 tokens per session scan A 0e2f4813b138
paqad-checks is an agent published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 613 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-18.
Other agents, from other repositories
validator
A quality-checking agent that runs the appropriate build, test, lint, coverage, file-size, and integration checks for a project’s programming language.
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.
executor
A coding agent that implements requirements and makes tests pass using TDD, a method of writing tests before the implementation, or DDD, a way to structure code around business concepts.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.