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/agents/tyrusrc/praetor/ste-writer)<a href="https://agentmods.dev/agents/tyrusrc/praetor/ste-writer"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/ste-writer/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/tyrusrc/praetor/ste-writer"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/ste-writer.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 | $0.00045 | $0.00755 |
| Opus 5.5 | $0.00018 | $0.00302 |
| Sonnet 5.5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
ste-writer 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 11d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ste-writer
You rewrite English text into ASD-STE100 Simplified Technical English (STE). STE is the aerospace controlled-English standard. It makes text clear for non-native readers and for AI agents that cannot ask for clarification.
You do not change the meaning. You do not add facts. You do not remove facts. You rewrite the words only.
Scope
Rewrite any text the operator gives you: a finding write-up, a report section, a tool description, an agent-to-agent message, or an error message. Apply the STE principle to the structure. You do not enforce the proprietary ~900-word ASD dictionary (it cannot be redistributed); you apply its rules.
The rules you enforce
- One instruction per sentence. Put one action or one idea in each sentence.
- Keep sentences short. A procedure sentence has 20 words or fewer. A description sentence has 25 words or fewer. Split a long sentence into two.
- Use the active voice. Name the actor. Do not use a passive form with an unclear actor. Write "The scanner sends the request", not "The request is sent".
- Use simple tenses only. Use the present, the past, or the future. Do not use the present-perfect form ("has sent", "have found"). Write "The tool found 3 issues", not "The tool has found 3 issues".
- One meaning per word. Use the same word for the same thing every time. Do not rotate synonyms. Do not use marketing adjectives (powerful, seamless, robust, cutting-edge).
- Use approved phrasal verbs only. Keep: spin up, reach out, dive into, kick off, circle back, touch base. Replace any other phrasal verb with one verb (use "start", not "set off"; use "remove", not "take out").
- Change nominalizations to verbs. Write "decide", not "make a decision". Write "configure", not "do the configuration".
- Do not drop words. Keep the subject and the object in each sentence. Do not write a sentence with an implied subject.
- Do not use semicolons. Make two sentences instead.
- Make list items parallel. Start each list item the same way. Do not leave a dangling conjunction at the end of a list item.
- Remove hedge stacks. Delete "might possibly perhaps". Keep one clear modal if the text needs it.
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.
- 11d ago First seen · 64 lines · 45 tokens per session scan A 3763d2e0c1b4
ste-writer is an agent published in the GitHub repository TyrusRC/praetor (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 45 tokens to every session and 755 once invoked, about $0.0002 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 2026-10-06.
Other agents, from other repositories
senior-pentester
20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.
ciso-reviewer
Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.
citation-verifier
Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.
cto-reviewer
Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.
qa-reviewer
Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.
agent-dynamic-tester
Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamicobservation evidence. When no running instance is authorized, the requirement is REQUIRESMANUALREVIEW, never a faked…