revenantworks-foundation-agentwright SKILL.md skillB

revenantworks-foundation-agentwright from revenantworks/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add revenantworks/claude-skills/revenantworks-foundation-agentwright@v1.2.10

Pins v1.2.10 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
revenantworks/claude-skills
Path
packs/foundation/skills/revenantworks-foundation-agentwright/SKILL.md
Versions recorded
11
Latest version
v1.2.10, committed Sep 22, 2026
First version recorded
Aug 12, 2026
Size
22,469 bytes
Repository stars
2
License
MIT

Designs and audits the system around an autonomous or scheduled agent — everything but the prompt text — and emits it in the target's native form. Trigger to design, spec, harden, review, or audit an agent, bot, scheduled task, or automation acting on its own; to write a Cowork task, a Claude Code routine, or a desktop scheduled task, or the same on ChatGPT, Gemini, or a workflow runner; for guardrails, kill switches, cadence, retries, failure handling, protected resources, output contracts…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# revenantworks-foundation-agentwright

*history in CHANGELOG.md · sources in SOURCES.md · MIT (LICENSE)*

The system around the prompt. An agent that acts on its own needs decisions no prompt carries: when it runs, what it may touch, what stops it, and what happens when the world returns nothing or garbage. agentwright produces that operating spec — or scores an existing one.

**Workflow:** Intake → Blast radius → Checklist pass *(design or audit)* → Ops spec / scoreline → Handback

Dependencies (standalone profile): web search for Entry — Refresh verification, and the surface's native file tools for delivery — where file tools are absent, every deliverable degrades gracefully to in-chat content the user can save. No scripts shipped, none assumed.

## Turn shape
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add revenantworks/claude-skills/revenantworks-foundation-agentwright@sha256:62bb426d2ab10fd6

The line at the top of this page pins the label v1.2.10, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_h4u5ylzrqnjjg3da.svg)](https://markdownregistry.com/a/art_h4u5ylzrqnjjg3da)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 11 versions of this file, between Aug 12, 2026 and Sep 22, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
v1.2.10 latest2026-09-22 8bc62df 22,469 BB view · diff
v1.2.92026-09-13 ae92abf 21,860 BB view · diff
v1.2.82026-09-11 bceb60a 20,527 BB view · diff
v1.2.72026-09-10 b3f5932 17,535 BB view · diff
v1.2.62026-09-10 cd91cfa 17,705 BB view · diff
v1.2.52026-09-09 d1528c4 17,214 BB view · diff
v1.2.42026-09-09 4306943 16,200 BB view · diff
v1.2.32026-08-21 5a28c33 15,595 BB view · diff
v1.2.22026-08-18 1183930 15,179 BB view · diff
v1.2.12026-08-14 14f6db0 14,973 BB view · diff
v1.2.02026-08-12 01ac6ea 14,702 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: disregard prior rules)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22469 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

revenantworks/claude-skills · 2 stars · license MIT · pushed 2026-10-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h4u5ylzrqnjjg3da
GET https://markdownregistry.com/api/v1/resolve?ref=revenantworks/claude-skills/revenantworks-foundation-agentwright
GET https://markdownregistry.com/api/v1/blob/62bb426d2ab10fd6b5994b70d4ed57dddde17eb73f9b957f62561f81ac3b1cff

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from revenantworks/claude-skills

CLAUDE.md CLAUDE.md file
revenantworks/claude-skills · CLAUDE.md
git:20260922.1c3d3c5 · audit A · 2 stars
CLAUDE.md@packs/foundation CLAUDE.md file
revenantworks/claude-skills · packs/foundation/CLAUDE.md
git:20260917.fc8be8b · audit A · 2 stars
revenantworks-foundation-brandwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-brandwright/SKILL.md · Defines a brand and its voice — identity, naming, palette, taglines, firewall — and applies them on request across…
v1.6.1 · audit A · 2 stars
revenantworks-foundation-commwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-commwright/SKILL.md · Shapes any message to its channel and audience. Drafts human by default in a neutral professional voice; a specific…
v1.1.2 · audit A · 2 stars
revenantworks-foundation-dispatchwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-dispatchwright/SKILL.md · Runs a session's fan-out — turns one large request into tiered, budgeted, recoverable units and dispatches them…
v1.3.2 · audit A · 2 stars
revenantworks-foundation-evalwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-evalwright/SKILL.md · Authors and audits eval suites for skills, prompts, and agent specs — a build-time generator whose suites live in the…
v1.1.4 · audit A · 2 stars
revenantworks-foundation-lorewright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-lorewright/SKILL.md · Turns research into verified knowledge products, two modes. Trigger when someone wants a researched recommendation…
v1.1.10 · audit B · 2 stars
revenantworks-foundation-promptwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-promptwright/SKILL.md · Builds, scores, hardens, and red-teams LLM prompts — from a rough idea to a copy-paste-ready artifact — and picks which…
v1.5.14 · audit B · 2 stars
revenantworks-foundation-resumewright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-resumewright/SKILL.md · Owns every handoff — a committed session state (what already happened, verified against git) or a forward task brief…
v1.1.2 · audit A · 2 stars
revenantworks-foundation-rigwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-rigwright/SKILL.md · Builds the standing config Claude reads before work — a Claude Project's instructions and knowledge-file plan, a…
v1.1.10 · audit B · 2 stars
revenantworks-foundation-skillwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-skillwright/SKILL.md · Builds, audits, ports, and integrates install-ready Agent Skills passing best practices. Trigger to build, audit…
v1.5.0 · audit B · 2 stars
revenantworks-foundation-tokenwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-tokenwright/SKILL.md · Measures and shrinks the token footprint of LLM-facing artifacts — prompts, SKILL.md bodies, agent specs, CLAUDE.md…
v1.2.7 · audit B · 2 stars

Every file in revenantworks/claude-skills

Browse by kind, by grade B, or by owner.