accept-gated-ai SKILL.md skillA

accept-gated-ai from tjcages/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tjcages/skills/accept-gated-ai@v0.2.0

Pins v0.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tjcages/skills
Path
accept-gated-ai/skills/accept-gated-ai/SKILL.md
Versions recorded
3
Latest version
v0.2.0, committed Aug 24, 2026
First version recorded
Jul 21, 2026
Size
2,229 bytes
Repository stars
6
License
none declared

Make write-access AI trustworthy: every edit diffed, accept-gated, reversible, proportional, and willing to do nothing. Use when designing or auditing an agent that creates/updates/deletes user data, when adding overnight/batch AI passes, when a product’s AI writes feel silent or over-eager, or when the user asks for accept-gates / EditProposal / proposal substrate / undo-before-delete. NOT for read-only Q&A bots or coding-agent repository isolation.

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

# Accept-gated AI

Chat: [RESPONSE.md](./RESPONSE.md). Full method: [METHODOLOGY.md](./METHODOLOGY.md).
Install slice: [agent-trust.template.md](./agent-trust.template.md).

## Operating order

### 1. Need write-access AI? (§1)

Read-only → skip. Silent enrichment already writing user fields → treat as leak audit (§9).

### 2. State the five laws (§2)

Diffed · accept-gated · original preserved · proportional+quiet · undo after accept.
Offer [agent-trust.template.md](./agent-trust.template.md) for `docs/agent-trust.md`.

### 3. Map write sites (§9)

Enumerate mutations. Classify: gated / interactive apply (§4.1) / declared exception / leak.

### 4. Substrate or fix (§3–§6)

Proposals: per-field diff, why, provenance, dedupe, stale refuse + conflict UX (§3.5).
Missing undo → block destructive verbs. Name §5 exceptions. Set volume/confidence (§3.6).

### 5. UI contract (§3.3)

AI marker · source/why · dismiss · optional volume. Blind accept is not a gate.

### 6. Score (§10)

Rubric ≥12/16, no load-bearing 0 on #1–#5. Log friction in EXAMPLES.md same day.

### 7. Hand off

Creed home → `constitution-first`. Gaps → Linear. Gate UX parity → `behavior-contracts`.

## Sub-flows
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tjcages/skills/accept-gated-ai@sha256:189ebb3cf550d86b

The line at the top of this page pins the label v0.2.0, 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_eovmjnitvoz5kcmi.svg)](https://markdownregistry.com/a/art_eovmjnitvoz5kcmi)

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

Versions

The registry has recorded 3 versions of this file, between Jul 21, 2026 and Aug 24, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
v0.2.0 latest2026-08-24 3625a0d 2,229 BA view · diff
v0.2.02026-07-21 955ead8 2,254 BA view · diff
v0.1.02026-07-21 4061b0e 2,199 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (2229 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

tjcages/skills · 6 stars · license none declared · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eovmjnitvoz5kcmi
GET https://markdownregistry.com/api/v1/resolve?ref=tjcages/skills/accept-gated-ai
GET https://markdownregistry.com/api/v1/blob/189ebb3cf550d86bcec5f74407c6f2d35ccdd7874b01cd9a35f738c7266b097d

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 tjcages/skills

AGENTS.md AGENTS.md file
tjcages/skills · AGENTS.md
git:20260918.148eea5 · audit A · 6 stars
CLAUDE.md CLAUDE.md file
tjcages/skills · CLAUDE.md
git:20260825.4659652 · audit A · 6 stars
CLAUDE.md@apple-native CLAUDE.md file
tjcages/skills · apple-native/CLAUDE.md
git:20260918.96bdb18 · audit A · 6 stars
apple-native SKILL.md skill
tjcages/skills · apple-native/skills/apple-native/SKILL.md · Build, adapt, or review native iOS and iPadOS apps with Apple frameworks and selectively retrieved components…
v0.1.0 · audit A · 6 stars
behavior-contracts SKILL.md skill
tjcages/skills · behavior-contracts/skills/behavior-contracts/SKILL.md · Keep multi-platform products behaviorally one product: write platform-neutral behavior contracts per form/primitive…
v0.1.0 · audit A · 6 stars
constitution-first SKILL.md skill
tjcages/skills · constitution-first/skills/constitution-first/SKILL.md · Author and govern a product North Star (constitution) that every feature is judged against — premise, non-negotiables…
v0.1.0 · audit A · 6 stars
CLAUDE.md@ea CLAUDE.md file
tjcages/skills · ea/CLAUDE.md
git:20260918.ca4af95 · audit A · 6 stars
ea SKILL.md skill
tjcages/skills · ea/skills/ea/SKILL.md · Route routine agent work to deterministic tools and bounded JEV decisions through the user’s preferred connection. Use…
v0.2.1 · audit A · 6 stars
CLAUDE.md@linear-methodology CLAUDE.md file
tjcages/skills · linear-methodology/CLAUDE.md
git:20260729.1d36dbe · audit A · 6 stars
linear-discipline SKILL.md skill
tjcages/skills · linear-methodology/skills/linear-discipline/SKILL.md · Always-on Linear session discipline and one-time soft nudge for untracked repos. Use whenever non-trivial work is…
v1.0.2 · audit A · 6 stars
linear-finish-install SKILL.md skill
tjcages/skills · linear-methodology/skills/linear-finish-install/SKILL.md · Finish Linear tracking pack install after skills are present: write always-on rules (Linear = default source of truth…
v1.0.2 · audit A · 6 stars
linear-methodology SKILL.md skill
tjcages/skills · linear-methodology/skills/linear-methodology/SKILL.md · Proven methodology for building and tracking features, projects, and issues in Linear. Use when the user wants to set…
v1.0.2 · audit A · 6 stars

Every file in tjcages/skills

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