Home / habitat-thinking / ai-literacy-superpowers · ai-literacy-superpowers/skills/sentinel-design/SKILL.md · GitHub

sentinel-design skillA

sentinel-design is agent-read markdown (skill) from habitat-thinking/ai-literacy-superpowers: Use when designing, reviewing, or classifying an agent that guards the human — defines the sentinel category, the three-part signature (S1 read-only, S2 advisory-to-human, S3 explicit honesty rule), the near-miss gallery that explains why read-only-plus-advisory is not sufficient, the honesty-rule-before-detection-logic discipline, and the three anti-patterns that eject an agent from the category.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Sentinel Design

Most agents in this plugin act on an artefact. The spec-writer edits a
spec, the tdd-agent writes tests, the integration-agent commits and
merges, the harness-gc rewrites stale documentation. Their object of
care is a thing in the repository, and you judge them by what they did
to that thing.

A **sentinel** is different. Its object of care is not the codebase, the
pipeline, or the harness — it is **the human**. A sentinel protects and
supports the understanding and judgement of the person in the workflow.
It informs, challenges, surfaces, or warns. It never fixes, writes,
merges, or decides.

> **Sentinel** — any agent whose primary purpose is to protect and
> support the understanding and judgement of the human in the workflow.

The category emerged organically. Four agents — the decision-discipline
triad (`carpaccio`, `advocatus-diaboli`, `choice-cartographer`) plus the
`reservoir-warden` — and later the `cost-estimator` were all built to
the same shape without anyone naming the shape. This skill names it, so
that the next one can be built deliberately rather than rediscovered.

## Why sentinels exist: the debts AI moves upstream
…

Read the whole file at its exact version.

How to install

Latest version
mdr add habitat-thinking/ai-literacy-superpowers/sentinel-design@git:20260823.6a0963e
Exact content
mdr add habitat-thinking/ai-literacy-superpowers/sentinel-design@sha256:ecc444a4c3ec8f8a

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_t73yzqf4yfx3t3ra.svg)](https://markdownregistry.com/a/art_t73yzqf4yfx3t3ra)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260823.6a0963e latest2026-08-23 6a0963e 15,525 BA view · diff
git:20260813.d867c7c2026-08-13 d867c7c 15,418 BA view · diff
git:20260809.8fa01122026-08-09 8fa0112 14,867 BA view · diff
git:20260720.88b52e82026-07-20 88b52e8 10,478 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15525 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 prompt-injection phrasing
  • 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

Source

GitHub

habitat-thinking/ai-literacy-superpowers · 106 stars · license NOASSERTION · pushed 2026-09-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t73yzqf4yfx3t3ra
GET https://markdownregistry.com/api/v1/resolve?ref=habitat-thinking/ai-literacy-superpowers/sentinel-design
GET https://markdownregistry.com/api/v1/blob/ecc444a4c3ec8f8a3e137646e5a382755d059549615bb844a13465059fe20b24

Your agent 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.

More from habitat-thinking/ai-literacy-superpowers

constraints rules
habitat-thinking/ai-literacy-superpowers · .cursor/rules/constraints.mdc · Architectural constraints synced from HARNESS.md
git:20260826.7eba676 · audit A · 106 stars
conventions rules
habitat-thinking/ai-literacy-superpowers · .cursor/rules/conventions.mdc · Project conventions synced from HARNESS.md
git:20260415.d0763a2 · audit A · 106 stars
AGENTS.md agents
habitat-thinking/ai-literacy-superpowers · AGENTS.md
git:20260814.d94de33 · audit A · 106 stars
CLAUDE.md claude
habitat-thinking/ai-literacy-superpowers · CLAUDE.md
git:20260826.7eba676 · audit A · 106 stars
advocatus-diaboli skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/advocatus-diaboli/SKILL.md · Use when acting as the adversarial spec reviewer — raises steel-manned objections across six categories before plan…
git:20260826.7eba676 · audit A · 106 stars
ai-literacy-assessment skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/ai-literacy-assessment/SKILL.md · This skill should be used when the user asks to "assess AI literacy", "run an assessment", "check literacy level"…
git:20260716.ca45e3c · audit A · 106 stars
auto-enforcer-action skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/auto-enforcer-action/SKILL.md · Use when setting up automatic PR constraint enforcement via GitHub Actions — covers the advisory-vs-blocking split…
git:20260615.36b92f7 · audit A · 106 stars
carpaccio skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/carpaccio/SKILL.md · Use when acting as the cadence governor — slices a raw task description into thin, end-to-end-complete pieces before…
git:20260526.40e858f · audit A · 106 stars
choice-cartographer skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/choice-cartographer/SKILL.md · Use when acting as the decision-archaeology agent — surfaces decisions a spec has made (including the silent ones)…
git:20260813.d867c7c · audit A · 106 stars
coda skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/coda/SKILL.md · Use when closing an agentic session deliberately rather than by attrition — carries the four-step ritual (survey, park…
git:20260812.cecd058 · audit A · 106 stars
cognitive-reservoir skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/cognitive-reservoir/SKILL.md · Use when watching the human verifier rather than the output — defines the observable proxies, the…
git:20260811.05a775b · audit A · 106 stars
component-design-with-tdad skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/component-design-with-tdad/SKILL.md · Use when designing a new plugin component (skill, agent, command, or backing script) for the ai-literacy-superpowers…
git:20260510.3655852 · audit A · 106 stars

Every file in habitat-thinking/ai-literacy-superpowers

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