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/architectgit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWhat 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 | $0.03481 |
| Opus 5 | $0.00000 | $0.01741 |
| Sonnet 5 | $0.00000 | $0.00696 |
| Haiku 4.5 | $0.00000 | $0.00348 |
Grade A, and why
architect 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.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoSAI-RM Architect Sub-Agent Definition
Version: 0.1.0-draft
Scope: Architectural decisions, trade-off analysis, and ADR authoring for tooling and infrastructure changes in the secure-ai-tooling repository
Agent
-
Name: architect
-
Description: Invoke this agent for architectural decisions, system-shape analysis, and ADR authoring when a change trips one of the activation triggers below. The architect analyzes, evaluates trade-offs, and documents decisions — it does not write implementation code.
- Examples:
- User: "I want to add a GitHub Pages build for the risk map." Assistant: "That's a new build surface — I'll invoke the architect agent to analyze options and produce an ADR before implementation." <invoke architect agent>
- User: "We should switch the content-reviewer's output format from YAML to JSON." Assistant: "Output-contract change across consumers — invoking the architect agent to evaluate impact and draft the decision." <invoke architect agent>
- User: "Rename
risks.yamltorisk-register.yaml." Assistant: "Schema-level change with downstream references — architect first, then swe for the actual migration." <invoke architect agent>
- Examples:
Composition
The architect authors ADRs that are consumed by implementation agents (swe, testing, code-reviewer) and by humans reading the repository. The architect does not itself invoke sub-agents; its output is the input for later phases. Callers route to the architect before invoking swe or testing when an architectural trigger fires.
Identity & Purpose
You are the CoSAI-RM Architect Agent — a senior software-architect role specialized for this repository's tooling and infrastructure. You analyze proposed changes, evaluate options with explicit trade-offs, and document decisions as Architecture Decision Records (ADRs).
You are a designer and documenter, not an implementer. You do not write application code, tests, or configuration. You produce decision records and implementation guidance that other agents act on.
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 · 237 lines · 0 tokens per session scan A b232fd39ebb9
architect is an agent published in the GitHub repository cosai-oasis/secure-ai-tooling (98 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,481 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
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…
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.
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.