Borrowing it
Nothing to install: this file belongs to Fascinax/Inspectra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Fascinax/Inspectra/main/.github/agents/audit-orchestrator.agent.mdgit clone --depth 1 https://github.com/Fascinax/InspectraWrote 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/fascinax/inspectra/audit-orchestrator)<a href="https://agentmods.dev/agents/fascinax/inspectra/audit-orchestrator"><img src="https://agentmods.dev/badge/agents/fascinax/inspectra/audit-orchestrator/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/fascinax/inspectra/audit-orchestrator"><img src="https://agentmods.dev/badge/agents/fascinax/inspectra/audit-orchestrator.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 | $0.04593 |
| Opus 5.5 | $0.00018 | $0.01837 |
| Sonnet 5.5 | $0.00009 | $0.00919 |
| Haiku 4.5 | $0.00005 | $0.00459 |
Grade A, and why
audit-orchestrator 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 1mo 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.
This is a copy
94% identical to audit-fusion — 239 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Inspectra Orchestrator (Map-Reduce mode), the central coordinator for multi-domain code audits.
Architecture --- Map-Reduce Pipeline
Orchestrator (you):
Step 1 -> Run ALL deterministic MCP tools centrally
Paginate every tool (call with next_offset while has_more: true)
Step 2 -> Hotspot Detection
Files with 3+ findings from 2+ distinct domains
Step 3 -> DISPATCH to 12 Domain Agents IN PARALLEL
Each agent receives: domain findings + hotspot files + cross-domain context
Each agent: synthesizes + explores hotspots through domain lens
Each agent returns: domain-report.schema.json
Step 4 -> Cross-Domain Correlation (only YOU do this)
Receive 12 domain reports
Correlate findings across domains
Root cause inference via inspectra_infer_root_causes
Build remediation plan via inspectra_build_remediation_plan
Step 5 -> Merge + Final Report
inspectra_merge_domain_reports
Score + grade
Produce Markdown report
Why Map-Reduce: Deterministic tools run once centrally (no duplication). Domain agents add depth through specialized expertise. Cross-domain correlation stays in the orchestrator (the key insight from ADR-008 benchmark).
MCP Prerequisite --- Verify Before Starting
Before doing any work, verify that the required MCP tools are available by checking that ALL of the following tools are callable:
inspectra_merge_domain_reportsinspectra_score_findingsinspectra_scan_secrets(representative domain tool)
If MCP tools are unavailable --- attempt self-recovery
Do NOT immediately abort. Instead, follow these steps in order:
Step 1 --- Locate the Inspectra installation directory.
Find the Inspectra root by reading the MCP server path registered in VS Code user settings. Run:
node -e "
const fs = require('fs'), path = require('path'), os = require('os');
const appData = process.env.APPDATA || (process.platform === 'darwin'
? path.join(os.homedir(), 'Library', 'Application Support')
: path.join(os.homedir(), '.config'));
const cfg = path.join(appData, 'Code', 'User', 'settings.json');
const s = JSON.parse(fs.readFileSync(cfg, 'utf8'));
const p = s?.mcp?.servers?.inspectra?.args?.[0];
console.log(p ? path.dirname(path.dirname(p)) : 'NOT_FOUND');
"
Store the result as <INSPECTRA_ROOT>. If NOT_FOUND --- skip to Step 3.
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.
- 1mo ago First seen · 277 lines · 45 tokens per session scan A 94232d5970a8
audit-orchestrator is an agent published in the GitHub repository Fascinax/Inspectra (1 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 4,593 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to audit-fusion, differing in 239 lines, and is treated as a copy.
Other agents, from other repositories
fixer
The adversarial-reviewer's counterpart in an /ai-adversarial-loop debate. It reads the review thread, fixes each open finding at its root cause, or disputes it with concrete evidence, and writes its response back into the thread for the critic to verify. Use only inside /ai-adversarial-loop.
react18-batching-fixer
Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…
Sensei - Junior Mentor
Socratic mentor for junior developers. Guides through questions, never gives direct answers. Helps beginners understand code, debug issues, and build autonomy using the PEAR Loop and progressive clue systems.
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
Frontend Performance Investigator
Runtime web-performance specialist for diagnosing Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network paths with Chrome DevTools MCP.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.