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/TyrusRC/praetorWrote 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/commands/tyrusrc/praetor/checklist)<a href="https://agentmods.dev/commands/tyrusrc/praetor/checklist"><img src="https://agentmods.dev/badge/commands/tyrusrc/praetor/checklist/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/commands/tyrusrc/praetor/checklist"><img src="https://agentmods.dev/badge/commands/tyrusrc/praetor/checklist.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 | $0.00000 | $0.00684 |
| Opus 5.5 | $0.00000 | $0.00274 |
| Sonnet 5.5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
checklist 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 17d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /checklist — a full-coverage pentest on $ARGUMENTS.
Goal: full-coverage testing against the latest OWASP standards + Praetor's KB
edge cases, ending in a single markdown checklist file the operator can read and
a client report. Follow .claude/rules/hunting.md and the command-engagement
skill throughout.
Phase 0 — confirm (R28/R32, ask once if unstated)
- Parse the target domain from the arguments. If no domain is given, ask for it.
- Determine scope: which surfaces are in play —
web,api,mobile,llm(any combination). If the arguments don't say, ASK the operator (state a default ofweb). This decides which standards go in the checklist. - Determine objective/depth: full-coverage-with-notes (default here) vs a named subset. Confirm mode (black/grey/white/hybrid) and whether creds / a second role / an API schema exist.
Phase 1 — recon gate (R20a)
load_target_intel(domain, "all") + check_target_freshness. If the workspace
is empty, run a recon pass (browser_crawl → full_recon →
discover_attack_surface) and save_target_intel before testing.
Phase 2 — build the checklist deliverable
Call build_engagement_checklist(domain, scope="<scope>"). This writes
.burp-intel/<domain>/reports/<domain>-checklist.md — the combined full list:
OWASP Top 10 (2025) + WSTG v4.2 for web, API Top 10 (2023) if api, MASVS/MASTG if
mobile, AI Testing Guide if llm, plus every applicable KB test class as edge
cases. Report the path to the operator.
Phase 3 — work the checklist to coverage
Loop with checklist_autotest(domain, standard) to get the next open items,
execute each with its mapped tool, and record results with
checklist_update / checklist_record_batch. Spend the majority of time on
impact classes (authorization, auth/session, business logic, injection-to-sink)
per R29 — header/TLS/version items are recon output, not the hunt. Every
confirmed finding goes through verify → assess_finding → save_finding.
Re-run build_engagement_checklist (or coverage_status) to refresh the file
as items are ticked.
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.
- 17d ago First seen · 51 lines · 0 tokens per session scan A d83c82fb2571
checklist is a command published in the GitHub repository TyrusRC/praetor (7 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 684 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 2026-09-29.
Other commands, from other repositories
launch
Parse all configs in the current engagement, dispatch senior-pentester subagents in parallel, run the validation chain, emit findings ready for /review.
start
Start a new firewall-review engagement. Argus greets the operator, asks all six scoping questions in one batch, scaffolds the engagement folder, and waits for configs. No arguments.
report
Render a consolidated customer-review Excel workbook, optional audit-grade PDF, and chain-of-custody manifest from approved findings. Gated on ≥1 approve in feedback.jsonl.
review
Triage findings in chat. Operator sees each finding with evidence, chooses approve / request-changes / other per finding (or batches).
pending
Curator commands for learning-loop candidates. Usage — /pending list | /pending review | /pending promote | /pending reject | /pending hold.
configure-chiliforms
Build a ChiliForms embed (a form Chili Piper generates from a Concierge router) for a customer without a form of their own, and get a ready-to-paste snippet. Read-only.