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 skills add JesusConwellpy/secagent-skills --skill secagent-orchestrationgit clone --depth 1 https://github.com/JesusConwellpy/secagent-skillsWrote 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/skills/jesusconwellpy/secagent-skills/secagent-orchestration)<a href="https://agentmods.dev/skills/jesusconwellpy/secagent-skills/secagent-orchestration"><img src="https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-orchestration/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/skills/jesusconwellpy/secagent-skills/secagent-orchestration"><img src="https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-orchestration.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 | $0.00028 | $0.00658 |
| Opus 5 | $0.00014 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
secagent-orchestration 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SecAgent Orchestration — Sub-agent Coordination
Loading this SKILL gives you multi-agent coordination capabilities.
Available Agent Types
spawn type parameter:
recon Recon: port scan, service discovery, subdomains, OSINT
web-analyst Web: SQLi/XSS/LFI/SSRF/CSRF detection
binary-analyst Binary: checksec, disassemble, ROP/shellcode
exploit-runner Exploit: PoC execution, vuln verification (sandboxed)
intel-gatherer Intel: CVE search, exploit-db, GitHub PoC
code-auditor Audit: source code vulnerability discovery
post-exploit Post-exploit: persistence, lateral movement
coordinator Coordination: team orchestration, evidence synthesis
general General: non-security-specific tasks
Orchestration Rules
Fan-Out (most important)
N independent tasks = N agent_spawn calls in the SAME turn. Never serialize.
Correct:
Same turn: spawn recon "target A" + spawn recon "target B" + spawn intel "CVE search"
→ 3 agents run in parallel
Wrong:
Wait for A → then spawn B → serial waste
Trigger Conditions
>1 target → spawn recon × N (parallel)
Product + version found → spawn intel-gatherer (immediately)
Hypothesis confidence ≥0.7 → spawn specialist for verification
Exploitation path clear → spawn exploit-runner
Binary file provided → spawn binary-analyst
Communication Protocol
After spawn, poll for completion:
agent_wait(id) → blocks until agent finishes, returns {id, status, result}
agent_result(id)→ pulls structured output for a completed agent
On completion:
1. Read result summary
2. Integrate — don't redo the sub-agent's work
3. Call agent_result(id) for full output if the summary is too thin
Verification Protocol
Iron rule: ONE hypothesis per agent.
1. spawn exploit-runner with EXACT CVE ID + target
2. Returns: success/failure + evidence
3. Success → CONFIRMED, advance
4. Failure → 3-step analysis:
a. Hypothesis wrong? → new hypothesis, new agent
b. Test wrong? → fix, retry
c. Target limited it? (WAF, patch, firewall) → different path or document exclusion
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.
- 9d ago First seen · 88 lines · 28 tokens per session scan A 059c3771b833
secagent-orchestration is a skill published in the GitHub repository JesusConwellpy/secagent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 658 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
osint-recon
A knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people.
secknowledge-skill
A knowledge base for testing the security of websites, software, and AI systems, including agents and language models.
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
client-reverse
A workflow for analysing and replaying requests made by mobile apps, browser JavaScript, or desktop clients during authorised security testing.
redteam-crypto-detail-pack
Domain routing and boundary guidance for authorized cryptography weakness testing, including weak algorithms, padding oracles, key management errors, insecure randomness, and hash collision risks. Use when a task belongs to the cryptography testing domain and needs scope, evidence, pivot, or exit criteria.
redteam-logic-detail-pack
Domain routing and boundary guidance for authorized business logic vulnerability testing, including race conditions, flow bypass, price tampering, permission logic errors, and bulk operation abuse. Use when a task belongs to the logic testing domain and needs scope, evidence, pivot, or exit criteria.