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 PANYUXIN6/pyx-skills --skill review-design-contractsgit clone --depth 1 https://github.com/PANYUXIN6/pyx-skillsWrote 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/panyuxin6/pyx-skills/review-design-contracts)<a href="https://agentmods.dev/skills/panyuxin6/pyx-skills/review-design-contracts"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/review-design-contracts/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/panyuxin6/pyx-skills/review-design-contracts"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/review-design-contracts.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 85 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 | $0.00115 | $0.02551 |
| Opus 5 | $0.00057 | $0.01275 |
| Sonnet 5 | $0.00023 | $0.00510 |
| Haiku 4.5 | $0.00012 | $0.00255 |
Grade A, and why
review-design-contracts 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 12d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Design Contracts
Run a quality-first design review without model voting or LLM-as-judge. Keep the target document unchanged throughout the review.
Select one operation
Choose exactly one mode from the user's explicit request and do not transition between modes implicitly:
review: run a new design review and leave the target unchanged.apply-fixes: validate and consume an accepted queue, edit the target, then stop and hand off to a separate reviewer task.verify-fixes: independently review an already edited target. Enter this mode only when the current task is explicitly asked to runverify-fixesand did not edit that target.
Completing apply-fixes never authorizes the same task to enter verify-fixes, even when the queued run directory is available.
Start a review
- Read
references/review-protocol.md. - Confirm the current Codex task exposes Native
spawn_agent,wait_agent, andinterrupt_agent. If any is unavailable, stop before creating a run. Do not fall back to a CLI or API model backend. - Resolve
<skill-directory>as the absolute directory containing thisSKILL.md. - Run the authority precheck in
references/review-protocol.md. Inspect the target's frontmatter and direct design links first. If the target identifies itself as a child or delegates a material contract without a resolvable path, perform only the bounded same-directory and declared-index search described there. Automatically include an unambiguous non-observed governing design backed by a direct relationship; otherwise treat the target as self-contained unless an unresolved external contract is material to the review. Do not invoke another skill for this precheck. - Check
docs/REPO_MAP.mdanddocs/ARCHITECTURE.mdin the target repository. If either is missing, invoke$repo-map-firstin repository-context bootstrap mode. If relevant map claims may be stale or contradictory, invoke repository-context validation mode. Preserve the review target and authority provenance. Observed maps may locate files but cannot establish normative authority. If repository context required for architecture review remains materially ambiguous, stop before creating a run and reportINSUFFICIENT_INPUT. - From the repository root, run:
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 261 B
- references/adversarial-result-legacy.schema.json 1.6 KB
- references/adversarial-result.schema.json 2.0 KB
- references/adversarial-role-legacy.md 902 B
- references/adversarial-role.md 1.2 KB
- references/architecture-fix-verification-role.md 1.2 KB
- references/architecture-merge-role.md 939 B
- references/architecture-role.md 1.3 KB
- references/architecture-shard-result.schema.json 1.3 KB
- references/architecture-shard-role.md 1.5 KB
- references/author-rebuttal-result.schema.json 772 B
- references/author-rebuttal-role.md 1023 B
- references/author-response.schema.json 2.5 KB
- references/candidate-finding.schema.json 3.9 KB
- references/contract-ledger.schema.json 1.2 KB
- references/evidence-card.schema.json 2.5 KB
- references/fix-verification-result.schema.json 1.4 KB
- references/fix-verification-role.md 1003 B
- references/human-rejection-reasons.json 1.6 KB
- references/insufficient-result.schema.json 445 B
- references/rejection-record.schema.json 1.7 KB
- references/review-protocol.md 18 KB
- references/self-consistency-result.schema.json 551 B
- references/self-consistency-role.md 1.4 KB
- review.config.json 735 B
- scripts/review-design.mjs 143 KB runs code
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.
- 12d ago First seen · 143 lines · 115 tokens per session scan A 975e02d5824f
review-design-contracts is a skill published in the GitHub repository PANYUXIN6/pyx-skills (6 stars, last pushed 6d ago), licensed MIT. It adds 115 tokens to every session and 2,551 once invoked, about $0.0006 per session on Opus 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…