Borrowing it
Nothing to install: this file belongs to fqmyysjjd/agent-feed. 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/fqmyysjjd/agent-feed/main/.agents/skills/design-review/SKILL.mdgit clone --depth 1 https://github.com/fqmyysjjd/agent-feedWrote 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/fqmyysjjd/agent-feed/design-review)<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/design-review"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/design-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.
<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/design-review"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/design-review.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 | $0.00031 | $0.00497 |
| Opus 5.5 | $0.00012 | $0.00199 |
| Sonnet 5.5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
design-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review Skill
Required Use
Use this skill after drafting or updating any design, protocol, planning, README, AGENTS, skill, rule, domain, or handoff-document change.
Required Reading
.agents/rules/outcome-boundary.md.agents/domain/README.md.agents/rules/context-loading.md.agents/project/architecture-boundaries.md.agents/rules/development-workflow.md.agents/rules/review-gates.md.agents/rules/evidence-gates.mdif external research is used.- The document being reviewed.
Core Rule
Do not silently complete unresolved design gaps.
The review's highest-priority question is:
Can the next development step proceed from this design without inventing missing decisions?
Before judging readiness, verify result fit:
- The document addresses the user's stated or clearly inferred goal, not just the visible artifact format.
- The document explains the real problem, outcome, or workflow it claims to support.
- Any missing decision, evidence, boundary, or user assumption that could change the result is called out as a gap.
- The document does not hide weak support behind polished wording, broad framing, or generic best practices.
- The proposed next action would actually move the user toward the intended result.
If yes, state that the design is ready for the next development step and stop.
If no, identify the blocking gaps. Close a gap directly only when all of these are true:
- The answer is already supported by existing source-of-truth files.
- The change stays inside the current Task Brief.
- The change does not alter public behavior, CLI/API contracts, architecture ownership, adapter behavior, verification gates, source-of-truth boundaries, persistence, security, release scope, or product positioning.
When any condition is false, do not fill the gap yourself. Apply .agents/rules/decision-gates.md and ask for the required decision.
Output
Return readiness judgment, current task boundary, findings or gaps, decision points requiring confirmation, safe next step, documents that should be updated, and whether the document can drive implementation.
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 · 54 lines · 31 tokens per session scan A 549858a6101b
design-review is a skill published in the GitHub repository fqmyysjjd/agent-feed (4 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 497 once invoked, about $0.0001 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
dxkit-action
Read a dxkit report and execute fixes — prioritize findings by severity, plan the fix sequence, run the fix, verify the score moved, re-baseline if appropriate. Supports a SCOPED pass to burn down one category at a time (dependency/BOM vulnerabilities, security, code quality, tests, docs), and a BASELINE-CLEANUP pass…
dxkit-allowlist
Manage the dxkit allowlist over its whole lifecycle — list, inspect, audit (including orphaned entries after a re-baseline), bulk-defer newly published dep-vuln advisories, remove stale entries, prune expired ones, and export Snyk-originated suppressions to a .snyk policy. Use when the user says "review our…
dxkit-checks
Declare and operate custom repo invariants as first-class guardrail gates — a project rule (a "no imports from X" check, an architecture script, a license audit) or the built-in per-language lint gate. Use when the user says "make our lint errors block the PR", "gate our custom check", "add a repo rule to the…
dxkit-pr
Open a pull request with a title + body grounded in the branch's real commits and diff — what changed, features implemented, findings fixed — plus a reviewer checklist and the dxkit guardrail/allowlist/score signals a reviewer needs. Use when the user says "raise a PR", "open a pull request", "create the PR", "write…
unvibe-review
Use when a project, system, document, or workflow feels bloated, over-engineered, tangled, or fragile despite "working," or when rounds of iteration/review have only ever ADDED and never removed — to find what can be cut, unified, or reframed. Any domain (code, writing, research, video, analysis, ops, decks).…
safe-change
Trace, implement, test, and independently review one bounded software change. Use for ordinary feature, bug-fix, or refactor work after the repository is bootstrapped; do not use for broad repository cleanup, production operations, or undefined rewrites.