approval-boundaries SKILL.md skillA
approval-boundaries from reply-team/jason-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add reply-team/jason-ai/approval-boundaries@git:20261114.6b52d5cPins git:20261114.6b52d5c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- reply-team/jason-ai
- Path
skills/business/approval-boundaries/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261114.6b52d5c, committed Nov 14, 2026
- First version recorded
- Sep 21, 2026
- Size
- 37,530 bytes
- Repository stars
- 9
- License
- MIT
Where an agent must stop and ask the user before acting, how an operation's approval class is derived from its reversibility and its reach, what a valid confirmation looks like, and the one case where acting first is correct. Covers previews, retries and idempotency keys, unattended runs, standing approvals and anomaly stop-rules. Use before any operation that reaches a real person, when deciding whether an approval still applies, or when configuring an agent to run without a human present.
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
# Approval boundaries > **Knowledge, not the enforced contract.** This skill names operations from the vendor-neutral > catalogue in `sdr-operations`, which says what an SDR operation *is*. What this runtime validates > and executes is the smaller set of JSON documents under `docs/contracts/operations/`; where the > two disagree, the contract is what decides. ## Purpose Automated outbound acts on real people, using the user's domain, accounts and reputation. This skill defines the boundary between what an agent may do on its own and what requires the user to say yes — once, explicitly, for a specific action. Approval is no longer a value an agent looks up. It is **derived** from two properties the contract already states: what an operation can undo, and how far it reaches. This skill is where that derivation is explained and applied, and where the rules that sit on top of it live — what a preview must contain, what counts as a confirmation, what may be done without one, and what changes when nobody is present. It exists as one skill rather than a paragraph repeated in every workflow, because a rule that lives in eleven places drifts in eleven directions. …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_5vll3gdyoh7bh5y5/3e7bec25c8047c30920befd14ab1e9cb4ae79a01feef170334222212edd40135.json
Then /plugin install approval-boundaries@markdownregistry-5vll3gdyoh7bh5y5 in Claude Code. It installs git:20261114.6b52d5c, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add reply-team/jason-ai/approval-boundaries@sha256:3e7bec25c8047c30The line at the top of this page pins the label git:20261114.6b52d5c, 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.
[](https://markdownregistry.com/a/art_5vll3gdyoh7bh5y5)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in reply-team/jason-ai/approval-boundaries since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of approval-boundaries from somewhere else? Ask it: where did my approval-boundaries come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 5 versions of this file, between Sep 21, 2026 and Nov 14, 2026, about one every 13 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261114.6b52d5c latest | 2026-11-14 | 6b52d5c | 37,530 B | A | view · diff |
| git:20261112.f46bee4 | 2026-11-12 | f46bee4 | 34,914 B | A | view · diff |
| git:20261102.e0633ba | 2026-11-02 | e0633ba | 32,818 B | A | view · diff |
| git:20261030.2d59c00 | 2026-10-30 | 2d59c00 | 30,100 B | A | view · diff |
| git:20260921.ff8a517 | 2026-09-21 | ff8a517 | 29,531 B | A | view |
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/approval-boundaries/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (37530 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
reply-team/jason-ai · 9 stars · license MIT · pushed 2026-11-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5vll3gdyoh7bh5y5 GET https://markdownregistry.com/api/v1/resolve?ref=reply-team/jason-ai/approval-boundaries GET https://markdownregistry.com/api/v1/blob/3e7bec25c8047c30920befd14ab1e9cb4ae79a01feef170334222212edd40135
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.