agnt: Skill for Claude Code

.claude/skills/security-boundary-review/SKILL.md

security-boundary-review is a skill for Claude Code from standardbeagle/agnt. It costs 49 tokens per session (960 once invoked), scanned A, original, Apache-2.0.

A review guide for changes involving security boundaries such as tenant access, server-side request forgery, content-security policies, or authentication checks. It focuses on testing whether the protection actually blocks dangerous paths.

In plain words
What is it for?
It helps review guards, test collisions and refusal paths, verify that dangerous side effects do not occur, and confirm that tests fail when a control is removed.
Why use it?
A passing test suite or self-review can miss attacks at the boundary between tenants, services, or security controls.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is standardbeagle/agnt's own configuration. It tells Claude Code how to work on agnt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agnt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to standardbeagle/agnt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/standardbeagle/agnt/main/.claude/skills/security-boundary-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/standardbeagle/agnt

Made for: Claude Code.

Wrote 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.

agentmods badge for security-boundary-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/standardbeagle/agnt/security-boundary-review/github.svg)](https://agentmods.dev/skills/standardbeagle/agnt/security-boundary-review)
Your own site
<a href="https://agentmods.dev/skills/standardbeagle/agnt/security-boundary-review"><img src="https://agentmods.dev/badge/skills/standardbeagle/agnt/security-boundary-review/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.

agentmods 80×15 button for security-boundary-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/standardbeagle/agnt/security-boundary-review"><img src="https://agentmods.dev/badge/skills/standardbeagle/agnt/security-boundary-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 960 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00960
Opus 5.5 $0.00020 $0.00384
Sonnet 5.5 $0.00010 $0.00192
Haiku 4.5 $0.00005 $0.00096

Measured 1mo ago against content hash 0a18bf5785ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-boundary-review 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 1mo 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.

.claude/skills/security-boundary-review/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security boundary review

A green suite and the author's self-review are necessary, not sufficient. Both rewinds on the publish epics landed on code that was already green. Attack the boundary the author's tests assume. Code-level rules live in .claude/rules/publish-security-review-lessons.md.

Reviewing a guard or boundary change

  1. Read the cited mechanism. Do not trust the description or the spec. Example: a claim of "replaces upstream CSP" pointed at a strip-merge that kept hostile directives.
  2. Attack the collision path, not the naming path. Tests often prove that you cannot name another tenant's resource. Also test what happens when two tenants' keys, digests or hashes collide.
  3. Assert the refusal's provenance. Ask: "If I deleted this control, would this assertion still pass?" In a layered path it usually would. Assert both of these:
    • the error names the control's verdict, e.g. "upstream refused";
    • the dangerous side effect was never reached, e.g. the dialer was called exactly once.
  4. Mutation-verify once. Revert the fix or break the guard, rerun, and confirm the test fails on a behavioural assertion rather than on a key-comparison line. Restore the tree afterwards.
  5. Assert coincidence premises. If a test depends on equal digests, colliding keys or the same timestamp, assert that premise first with t.Fatalf("premise broken: ...").
  6. Never pin a value by the symbol that produces it. Spell the expected security constant as a literal. A test that compares against proxiedUpstreamStyleSrc passes any mutation of it.
  7. Name the field you mean. Assert on the directive or field itself, e.g. script-src sources are all hashes. A document-wide substring such as "no unsafe-inline anywhere" breaks the day an unrelated directive legitimately gains it.

Security docs

  • A sentence describing a shipped control's scope is load-bearing. Grep the guard's production callers and check the claim against the call sites. The count is usually one.
  • The tell is coverage words: "every", "all", "the same guard also".
  • When CSP-adjacent behaviour is enforced at two layers (validator or renderer first, then the header), state which one refuses first.
  • One false claim obliges a whole-doc sweep for that claim's shape. Fixing only the cited line blesses its siblings.
  • Fix a false claim by naming the real gap, the silent failure it hides, and the tracking task id. Never delete the sentence.

Read the full file on GitHub · 45 lines

Changes

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.

  1. 1mo ago First seen · 45 lines · 49 tokens per session scan A 0a18bf5785ad

Subscribe to this mod's changes

security-boundary-review is a skill published in the GitHub repository standardbeagle/agnt (22 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 960 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 2026-09-29.

Related

Other skills, from other repositories

printing-press-output-review

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…

mvanhorn/cli-printing-press · 102 tokens

code-review

You are a senior code reviewer. You receive diffs via stdin.

jrswab/axe · 0 tokens

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens

ring:verifying-code

Verifying a Go project: runs every quality check (lint, vet, imports, format, docs, unit, integration, E2E) and returns a single MERGEREADY or NEEDSFIX verdict. Report-only: never fixes anything. Use for a quick pre-merge or pre-PR check outside a full dev-cycle. Skip when not a Go project, when you want a single…

LerianStudio/ring · 101 tokens

pixiv-cli-pr

Prepare, update, or verify a pixiv-cli pull request using its current template, trusted verification policy, reviewed diff, and head-specific check results. Use for contributor handoff or PR readiness; merging, live /test execution, and releases are separate actions.

FlanChanXwO/pixiv-cli · 57 tokens

ci-orchestrator

Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.

pilinux/gorest · 32 tokens