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 skills/lukasrepublic/agentic-foundry/auditnpx skills add lukasrepublic/agentic-foundry --skill auditgit clone --depth 1 https://github.com/lukasrepublic/agentic-foundryWrote 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/lukasrepublic/agentic-foundry/audit)<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/audit"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/audit.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 | $0.00191 | $0.08459 |
| Opus 5 | $0.00096 | $0.04229 |
| Sonnet 5 | $0.00038 | $0.01692 |
| Haiku 4.5 | $0.00019 | $0.00846 |
Grade A, and why
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 3d 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/foundry:audit — the dormant-invocable deep audit (NOT the default review)
Binding disposition: this multi-pass engine is no longer the default review path.
/foundry:spec-review(skills/spec-review/SKILL.md) is now the default review verb before front-authorization — a single-pass Phase-0-lints + three-question fan-out + one remediation round. This engine's own empirical record is why: 0 of 17 real v2 runs CONVERGED, every documented paying finding landed in rounds 1–2 (87% within 2 rounds), and rounds 3+ demonstrably regenerated findings rather than resolving them. It is kept dormant-invocable — the operator may still run/foundry:audit <spec>directly for an exceptional deep audit (a genuinely contested atom where the operator wants the full five-phase sweep) — but it is never triggered automatically, never the mandatory gate before authorization, and never the assumed step in a normal atom's pipeline.workflows/spec-audit.jsitself is unmodified (denied path — it stays byte-identical, available for this dormant invocation).
The native-Workflow realization of the deep spec audit engine, as originally built. The
orchestration — an ordered phased sweep + remediate-between-passes + a deterministic guard
control-plane — is the Workflow tool; the phase prompts are the foundry layer. This engine is
NOT read-only and remediation is NOT a separate step: it runs the audit as a PHASED
remediate-between-passes loop whose default mode is GUARDED-AUTO (a background run that
reports the remediated spec + the diff the operator reviews at /foundry:authorize).
Operator-steer is an OPT-IN sibling mode — a per-phase REVIEW of the engine's remediations via
native AskUserQuestion (approve / reject / stop + "Other"-as-edit) that grants NO
elevated authority and SURFACES-AND-HALTS every high-blast outcome to the real channels; see
Operator-steer mode below.
The five phases (ORDERED, sequential)
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.
- 3d ago First seen · 408 lines · 191 tokens per session scan A 32794aa5ac08
audit is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 2d ago), licensed MIT. It adds 191 tokens to every session and 8,459 once invoked, about $0.0010 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
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.