identity-and-guardrails SKILL.md skillB
identity-and-guardrails from tylerjrbuell/reactive-agents-ts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tylerjrbuell/reactive-agents-ts/identity-and-guardrails@v2.0Pins v2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tylerjrbuell/reactive-agents-ts
- Path
apps/docs/skills/identity-and-guardrails/SKILL.md- Versions recorded
- 3
- Latest version
- v2.0, committed Jul 20, 2026
- First version recorded
- Mar 5, 2026
- Size
- 5,819 bytes
- Repository stars
- 31
- License
- MIT
Enable prompt injection detection, PII masking, behavioral contracts, kill switch controls, and audit logging for safe production deployments.
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
# Identity and Guardrails
## Agent objective
Produce a builder with guardrails, behavioral contracts, and safety controls correctly configured so the agent operates within defined bounds and can be stopped when needed.
## When to load this skill
- Deploying an agent in a multi-tenant or public-facing context
- Restricting which tools an agent can call or which topics it can address
- Requiring human approval before certain tool calls
- Needing runtime pause/resume/stop controls
- Enforcing token/iteration/output-length budgets at the contract level
## Implementation baseline
```ts
import { ReactiveAgents } from "@reactive-agents/runtime";
const agent = await ReactiveAgents.create()
.withName("assistant")
.withProvider("anthropic")
.withReasoning({ defaultStrategy: "adaptive" })
.withTools({ allowedTools: ["web-search", "http-get", "file-read", "checkpoint"] })
.withGuardrails({
injection: true, // detect prompt injection attempts
pii: true, // detect and mask PII in inputs/outputs
toxicity: true, // detect toxic content
})
.withBehavioralContracts({
deniedTools: ["file-write", "shell-execute"],
maxToolCalls: 30,
…Read the whole file at its exact version.
How to install
mdr add tylerjrbuell/reactive-agents-ts/identity-and-guardrails@sha256:eb4dc57a0d1b0e48The line at the top of this page pins the label v2.0, 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.
[](https://markdownregistry.com/a/art_e3xs7le57uddz77n)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Mar 5, 2026 and Jul 20, 2026, about one every 68 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.0 latest | 2026-07-20 | 80337d2 | 5,819 B | B | view · diff |
| v2.0 | 2026-04-10 | edbdd5f | 5,960 B | B | view · diff |
| v1.0 | 2026-03-05 | 768304b | 3,826 B | B | view |
Audit of the latest version
- fail: No prompt-injection phrasing (matched: ignore previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5819 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
tylerjrbuell/reactive-agents-ts · 31 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_e3xs7le57uddz77n GET https://markdownregistry.com/api/v1/resolve?ref=tylerjrbuell/reactive-agents-ts/identity-and-guardrails GET https://markdownregistry.com/api/v1/blob/eb4dc57a0d1b0e488188d434cacc9d1ca7ebfbad565c74e8c897411c1b5a5f01
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.