Borrowing it
Nothing to install: this file belongs to TalonT-Org/AutoSkillit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TalonT-Org/AutoSkillit/main/.claude/skills/design-guards/SKILL.mdgit clone --depth 1 https://github.com/TalonT-Org/AutoSkillitWrote 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/talont-org/autoskillit/design-guards)<a href="https://agentmods.dev/skills/talont-org/autoskillit/design-guards"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/design-guards/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/talont-org/autoskillit/design-guards"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/design-guards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00051 | $0.00981 |
| Opus 5.5 | $0.00020 | $0.00392 |
| Sonnet 5.5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
design-guards 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Guards Skill
Take a bug pattern audit report and design architectural guards that make each pattern structurally impossible or instantly caught. This is a multi-pattern analysis driven by a pattern report rather than a single bug investigation.
When to Use
- After
/audit-bugsproduces a bug pattern report - User says "design guards", "design defenses", or "guard against these patterns"
- User wants architectural immunity for a set of identified bug patterns
Arguments
Path to a bug pattern audit report (typically under temp/audit-bugs/). If not specified, use the most recent temp/audit-bugs/bug_pattern_audit_*.md.
Critical Constraints
NEVER:
- Modify any source code files
- Propose bandaid fixes or direct-only patches
- Create files outside
temp/design-guards/directory
ALWAYS:
- Use subagents for parallel codebase exploration
- Focus on structural immunity over one-off fixes
- Each guard must be concrete and testable
- All output goes under
temp/design-guards/(create if needed) - Final report:
temp/design-guards/defense_guards_{YYYY-MM-DD_HHMMSS}.md - Subagents must NOT create their own files - they return findings in their response text only
- Do not change any code
Workflow
Step 1: Parse the Bug Pattern Report
Read the input report and extract each pattern:
- Pattern name and description
- Affected components and sessions
- The root architectural gap identified
Step 2: Investigate Each Pattern in Parallel
For each pattern (or group of related patterns), launch subagents to explore:
Current State
- Find all current instances of the pattern in the codebase (not just the ones that already caused bugs)
- Map which components are vulnerable to this pattern today
Existing Guards
- What tests, contracts, or validation already exists for this area?
- Why did existing guards miss these bugs?
Architectural Solutions
- How do well-designed parts of the codebase prevent similar issues?
- What structural pattern would make this class of bug impossible?
- What's the minimum change that provides maximum coverage?
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.
- 1mo ago First seen · 128 lines · 51 tokens per session scan A 71858df112e6
design-guards is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 981 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.