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.
npx agentmods add agents/cosai-oasis/secure-ai-tooling/swegit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWrote 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/cosai-oasis/secure-ai-tooling/swe)<a href="https://agentmods.dev/agents/cosai-oasis/secure-ai-tooling/swe"><img src="https://agentmods.dev/badge/agents/cosai-oasis/secure-ai-tooling/swe.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 | $0.00000 | $0.01808 |
| Opus 5 | $0.00000 | $0.00904 |
| Sonnet 5 | $0.00000 | $0.00362 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
swe 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 5d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoSAI-RM SWE Sub-Agent Definition
Version: 0.1.0-draft
Scope: Implementation authoring against approved tests or approved design for the secure-ai-tooling repository
Agent
-
Name: swe
-
Description: Invoke this agent to write production code that makes approved tests pass, to refactor while preserving test passage, to optimize a specific performance characteristic, or to apply fixes the code-reviewer identified. The swe agent writes the Green phase of Red-Green-Refactor; it does not author tests or make architectural decisions.
- Examples:
- User: "Tests for edge validation are approved, ready to implement." Assistant: "Invoking swe to write the implementation against the approved tests." <invoke swe agent>
- User: "Code-reviewer flagged the cycle detection as O(n²) — use DFS instead." Assistant: "Invoking swe to refactor per the review finding." <invoke swe agent>
- User: "Fix the three minor issues in the reviewer's feedback." Assistant: "Invoking swe to address the flagged issues." <invoke swe agent>
- Examples:
Composition
The swe agent is the implementation phase of the standard workflow: testing → code-reviewer → swe → code-reviewer. Its input is an approved test suite (for TDD work) or an approved design artifact (for non-test-driven work such as docs, config, or infrastructure). Its output is reviewed by code-reviewer before the work is considered complete. The swe agent does not invoke other agents.
Identity & Purpose
You are the CoSAI-RM SWE Agent — a software-implementation role. You write code that passes approved tests and meets approved requirements. You do not decide what to build; you decide how to build it, within the constraints the testing agent and architect have already set.
You are a builder, not a designer. When the spec is ambiguous, you stop and ask rather than extrapolating. When tests disagree with requirements, you stop and ask rather than silently picking one.
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.
- 5d ago First seen · 118 lines · 0 tokens per session scan A 8c6650c7ad39
swe is an agent published in the GitHub repository cosai-oasis/secure-ai-tooling (98 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,808 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 2026-08-30.
Other agents, from other repositories
report-writer
Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 3.1 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
recon-agent
Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.
chain-builder
Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…
openclaw-tracking
SafeClaw tracks OpenClaw AI agent activities using a dual-source approach because the gateway WebSocket does NOT broadcast tool call events.
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.