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 Eliyce/paqad-ai --skill permission-boundary-reviewgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/permission-boundary-review)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/permission-boundary-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/permission-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.
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/permission-boundary-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/permission-boundary-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 | $0.00016 | $0.00551 |
| Opus 5 | $0.00008 | $0.00275 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
permission-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 9d 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.
What it actually says
What It Does
Reviews permission, authorization, and tenant-boundary expectations so pentest findings can focus on real access-control gaps instead of generic auth reminders.
Use This When
Use this when module docs or route inventories describe privileged actions, admin surfaces, policy checks, or tenant-specific data handling.
Inputs
- Read the module docs that describe privileged flows first.
- Read
references/boundary-checklist.mdbefore deciding whether evidence is sufficient. - Read tests and route evidence that show how the project enforces those boundaries.
Procedure
- Run
scripts/scan-authz-smells.shto surface candidate IDOR / hidden-admin / impersonation / broad-export / cross-tenant patterns. - For each hit, walk the relevant module docs to determine whether code, tests, or runtime evidence proves the boundary.
- Bucket each finding into an area from
assets/area-rubric.txt(idor, privilege-escalation, tenant-isolation, hidden-admin, impersonation, broad-export). - Treat doc-vs-implementation disagreement as a security finding, never a benign inconsistency.
- Format per
assets/output.template.md; validate withscripts/lint-findings.sh.
Output Contract
- Match
assets/output.template.md: severity, WSTG-AUTHZ id, area fromassets/area-rubric.txt, Evidence, Missing proof, Required action. - Output must pass
scripts/lint-findings.sh(exit 0).
Escalate / Stop Conditions
- Ask when the privilege model is unclear or not described anywhere in the project.
- Warn when runtime evidence suggests a privileged path is exposed without clear protection.
- Do not mark a boundary as safe purely because authentication exists.
Resources
references/boundary-checklist.mdscripts/scan-authz-smells.shscripts/lint-findings.shassets/output.template.mdassets/area-rubric.txtagents/openai.yaml
What ships with it
6 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.
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.
- 9d ago First seen · 66 lines · 16 tokens per session scan A 46449655b735
permission-boundary-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 551 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
api-design
A guide to designing web APIs—the interfaces that let software systems exchange data—using REST, gRPC, and GraphQL patterns.
latency-analysis
Analyze endpoint latency trends using historical check data from memory. Detects slow degradation, spikes vs sustained issues, and calculates baseline deviations.
response-validation
Validate API response structure and content. Detects schema drift, unexpected null values, and abnormal response sizes.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
api-contract-testing
Curl-based HTTP endpoint probing and response validation. Tests status codes, response bodies, headers, and schema conformance against expected contracts.
Architecture Designer
Designs system-level structures including modules, services, data flow, and scaling strategy before implementation begins.