Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add canyonroad/agentsh --skill agentsh-policy-editgit clone --depth 1 https://github.com/canyonroad/agentshWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/canyonroad/agentsh/agentsh-policy-edit)<a href="https://agentmods.dev/skills/canyonroad/agentsh/agentsh-policy-edit"><img src="https://agentmods.dev/badge/skills/canyonroad/agentsh/agentsh-policy-edit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/canyonroad/agentsh/agentsh-policy-edit"><img src="https://agentmods.dev/badge/skills/canyonroad/agentsh/agentsh-policy-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 56 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01551 |
| Opus 5.5 | $0.00017 | $0.00620 |
| Sonnet 5.5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
agentsh-policy-edit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit AgentSH Policy
Overview
Make targeted edits to existing AgentSH security policies — add, remove, or update rules and declarations. Understands first-match-wins policy categories plus the separate Postgres-family database rule semantics.
When to Use
- User asks to add/remove/update a policy rule ("allow stripe.com", "block file deletes")
- User asks to change declared HTTP API access (
http_services,providers) - User asks to change Postgres-family DB access (
db_services,database_rules,database_connection_rules,policies.db) - User wants to change resource limits or audit settings
- User mentions modifying an existing policy
- NOT for creating new policies from scratch (use agentsh-policy-create)
Flow
-
Locate & read the policy
- Check
config.yml/config.yamlforpolicies.dir - If not found, look for
configs/policies/directory - Fall back to asking the user
- If multiple policies exist, list them and ask which one to edit
- Read the full YAML into context
- Check
-
Understand the intent Map the user's request to:
- Rule category — file_rules, network_rules, command_rules, unix_socket_rules, registry_rules, signal_rules, dns_redirects, connect_redirects, http_services, providers, db_services, database_rules, database_connection_rules, policies.db, resource_limits, env_policy, audit, mcp_rules, package_rules, process_contexts, process_identities, env_inject, transparent_commands
- Operation — add a new rule, remove an existing rule, or modify an existing rule
- Insertion position — where in the rule order (for new rules)
-
Determine insertion position (for new rules) First-match-wins means ordering matters:
- Place deny rules before any broader matching rule regardless of its decision — any non-deny rule (
allow,approve,redirect,audit,absorb,soft_delete) that matches first will shadow the deny - Place allow rules before the default-deny catch-all at the end
- Place more specific rules before less specific ones
- When in doubt: deny rules go before the first non-deny rule in that category; allow rules go before the default-deny
- Do not apply this first-match-wins shortcut to
database_rulesordatabase_connection_rules; see DB rules below.
- Place deny rules before any broader matching rule regardless of its decision — any non-deny rule (
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 103 lines · 42 tokens per session scan A acaeb66f3d73
agentsh-policy-edit is a skill published in the GitHub repository canyonroad/agentsh (404 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,551 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
python-development
Workflow guidance for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files under python/.
security-conductor
Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".