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 WizTheAgent/IronMesh --skill ironmesh-auditgit clone --depth 1 https://github.com/WizTheAgent/IronMeshWrote 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/wiztheagent/ironmesh/ironmesh-audit)<a href="https://agentmods.dev/skills/wiztheagent/ironmesh/ironmesh-audit"><img src="https://agentmods.dev/badge/skills/wiztheagent/ironmesh/ironmesh-audit/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/wiztheagent/ironmesh/ironmesh-audit"><img src="https://agentmods.dev/badge/skills/wiztheagent/ironmesh/ironmesh-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00722 |
| Opus 5 | $0.00020 | $0.00361 |
| Sonnet 5 | $0.00008 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
ironmesh-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IronMesh audit log
Reads the last N entries from the HMAC-chained audit log. Used for
security investigations — every entry is chained to the previous via
HMAC-SHA256, so tampering breaks the chain and ironmesh audit verify
will flag it.
When to use
- User reports "can't connect to X" — look for
TOFU_MISMATCHorAUTH_BLOCKED - Investigating a peer that went offline — look for
PEER_DROPPED_LONG - Security review — look for any unexpected
KEY_ROTATION,REPLAY_DETECTED, orDECRYPT_FAILURE
How to run
: "${IRONMESH_AUDIT_LOG:=$HOME/.ironmesh/audit.log}"
LIMIT="${1:-50}"
FILTER="${2:-}" # optional: grep filter (e.g. TOFU_MISMATCH)
if [ ! -f "$IRONMESH_AUDIT_LOG" ]; then
echo "No audit log at $IRONMESH_AUDIT_LOG"
exit 1
fi
tail -n "$LIMIT" "$IRONMESH_AUDIT_LOG" \
| ( [ -n "$FILTER" ] && grep -i "$FILTER" || cat ) \
| python3 -c "
import json, sys, datetime
for line in sys.stdin:
try:
e = json.loads(line)
ts = datetime.datetime.fromtimestamp(e['timestamp']).strftime('%Y-%m-%d %H:%M:%S')
event = e.get('event', '?')
data = e.get('data', {})
print(f'{ts} {event:<22} {json.dumps(data)}')
except Exception:
print(f'(unparseable) {line.rstrip()}')
"
Known events
| Event | Meaning |
|---|---|
STARTUP / SHUTDOWN |
Daemon lifecycle |
PEER_CONNECT / PEER_DISCONNECT |
Normal peer state changes |
PEER_DROPPED_LONG |
Peer offline past threshold (default 5 min) — investigate |
TOFU_NEW_PEER |
First time we saw this peer identity — normal at init |
TOFU_MISMATCH |
MITM candidate — peer presented a different key than pinned |
AUTH_FAILURE |
Wrong passphrase or malformed challenge |
AUTH_IP_BLOCKED |
3 auth failures in 5 min → IP blocked for 5 min |
DECRYPT_FAILURE / E2E_DECRYPT_FAILURE |
Ciphertext failed verification — protocol bug or attacker |
SIGNATURE_FAILURE |
Ed25519 signature didn't verify |
REPLAY_DETECTED |
Replayed sequence number or timestamp |
KEY_ROTATION |
Session key rotated (expected periodically) |
ROUTE_ANNOUNCED / ROUTE_LEARNED / ROUTE_EXPIRED |
Mesh routing table changes |
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 · 74 lines · 40 tokens per session scan A f39c067eef39
ironmesh-audit is a skill published in the GitHub repository WizTheAgent/IronMesh (22 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 722 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
draw-image
Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.
design-taste-frontend
Use for visual design direction on greenfield, user-facing surfaces — marketing and landing pages, generated apps, portfolio-style or standalone pages. NOT for routine Archestra platform UI work (dashboards, data tables, settings, forms, existing components) — use archestra-dev-frontend for that. Upstream intent…
managing-archestra-releases
Runs rolling beta releases, stable patches, and complete stable-line cutovers. Use when backporting fixes, cutting or retiring release branches, configuring release protections, testing artifacts, recovering failed runs, or approving releases.
archestra-dev-rust-napi
Use when editing Rust in this repo — the NAPI crates under platform/archestra-rs (app-runtime, image, and sandbox core/-rs crate pairs plus napi-loader, with their generated TypeScript bindings) or the standalone ai-labs Rust workspace (core/runner/cli/analyzer/dashboard) — including Rust build/test checks.
archestra-dev-testing
Use when deciding whether a change needs a test and at which level — unit, backend route-level integration, MSW-backed frontend integration, or e2e — or when reviewing tests for the "fluff test" anti-pattern. Start here before archestra-dev-backend-tests or archestra-dev-e2e.
migrate-to-archestra
Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance. Use when the user wants to move, port, or convert an existing agentic setup into an Archestra pilot.