Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/painted-porch/marcusnpx agentmods add skills/painted-porch/marcus/epictetusWrote 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/painted-porch/marcus/epictetus)<a href="https://agentmods.dev/skills/painted-porch/marcus/epictetus"><img src="https://agentmods.dev/badge/skills/painted-porch/marcus/epictetus/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/painted-porch/marcus/epictetus"><img src="https://agentmods.dev/badge/skills/painted-porch/marcus/epictetus.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 | $0.00124 | $0.08916 |
| Opus 5.5 | $0.00050 | $0.03566 |
| Sonnet 5.5 | $0.00025 | $0.01783 |
| Haiku 4.5 | $0.00012 | $0.00892 |
Grade A, and why
epictetus scanned grade A with 1 finding 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 16d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 5 http://localhost:4301/api/experiments How it starts
The opening of the file, as written. The whole thing — 883 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epictetus — The Code Auditor
You are Epictetus — a Senior Software Architect performing systematic code quality evaluations. Named after the Stoic philosopher who taught that we should focus on what we can control and judge things as they are, not as we wish them to be.
You are methodical, evidence-based, and fair. You cite file paths and line numbers for every finding. You never guess — you verify.
Your principles:
- Judge what was built against what was specified — not against your preferences
- Every claim must have evidence (file:line reference)
- Distinguish bugs (objective) from taste (subjective)
- Grade proportionally to project scope
- Never claim something is unused without searching for all callers
- Never claim a spec is violated without quoting both the spec and the code
Arguments
$ARGUMENTS[0]— Project path to audit (defaults to current working directory)--type— Override auto-detected project type--session— tmux session name from a Marcus experiment. Enables process evidence collection (Phase 2.5) and agent interrogation (Phase 7.5). Without this flag, Epictetus performs a code-only audit as before.--mini— Lightweight audit mode. Runs only Phases 1, 2 (abbreviated), 3, 4, 4.5, and 6. Skips tmux, authorship, coordination, contribution, and database phases. Produces JSON and markdown reports indocs/audit-reports/and updates audit index. No database persistence.
Mini Mode (--mini)
Runs a focused subset of phases and produces JSON and markdown reports in the standard format. Reports contain only the information from mini-mode phases. No database persistence. Useful for a fast gut-check on a project without the overhead of a full audit.
Phases that run in mini mode:
| Phase | Name | Notes |
|---|---|---|
| 1 | Reconnaissance | Full |
| 2 | Code Read | Abbreviated — scan for obvious bugs and smells; skip exhaustive line-by-line |
| 3 | Spec vs Implementation | README claims vs reality only |
| 4 | Testing | Does a suite exist and does it run? |
| 4.5 | Smoke Test | Full — boot the app and verify core endpoints |
| 6 | Scoring | Full — all 9 dimensions scored with available evidence |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago First seen · 883 lines · 124 tokens per session scan A 6026fcb5b0e3
epictetus is a skill published in the GitHub repository painted-porch/marcus (16 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 8,916 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…