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 Sefyu24/master-iam-skills --skill review-access-controlgit clone --depth 1 https://github.com/Sefyu24/master-iam-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/sefyu24/master-iam-skills/review-access-control)<a href="https://agentmods.dev/skills/sefyu24/master-iam-skills/review-access-control"><img src="https://agentmods.dev/badge/skills/sefyu24/master-iam-skills/review-access-control/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/sefyu24/master-iam-skills/review-access-control"><img src="https://agentmods.dev/badge/skills/sefyu24/master-iam-skills/review-access-control.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 | $0.00103 | $0.01393 |
| Opus 5 | $0.00051 | $0.00696 |
| Sonnet 5 | $0.00021 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
review-access-control 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Access Control
Turn business access rules into evidence, permission decisions, and tests. Give a practical IAM result instead of generic security advice.
Set the boundary
- Work only on systems and artifacts that the user is authorized to inspect.
- Use source review, local tests, and user-approved test environments.
- Do not attempt to bypass controls on a live service.
- Do not expose credentials, tokens, secrets, or unnecessary personal data.
- Treat this as focused access-control work, not a complete security or compliance assessment.
- If the user requests only a review, do not modify code.
- If the user requests a fix, make the smallest durable change and add a denied-path test.
Choose the outcome
Use one or more paths:
- Inspect: Find access-control weaknesses and support each conclusion with evidence.
- Model: Define actors, protected resources, actions, policy inputs, enforcement points, lifecycle rules, and tests.
- Learn: Explain IAM through the decisions present in a lab, design, or implementation.
Read guides/clear-technical-english.md before producing a user-facing answer.
For an inspection, read guides/review-playbook.md.
For a permission design, read guides/permission-modeling.md.
For identity, authentication, federation, lifecycle, or non-human access context, read guides/identity-context.md.
Establish expected behavior
Do not treat existing code as the intended policy.
Use this evidence order:
- Rules supplied or approved by the user
- Product requirements and access-policy documents
- Authorization tests and acceptance criteria
- Consistent server-side behavior
- Names, comments, and interface labels
Record an unresolved rule as a policy question. Do not label uncertainty as a confirmed vulnerability.
Build an access map
Identify:
- Actors: people, administrators, services, workloads, integrations, and agents
- Identity context: authenticated identity, active organization, session, client, assurance, and delegation
- Resources: records, files, collections, exports, configuration, secrets, and administrative functions
- Actions: list, read, create, change, remove, approve, share, export, assign, impersonate, and administer
- Policy inputs: roles, attributes, relationships, ownership, organization, resource state, risk, and time
- Control points: request handlers, middleware, service methods, policy engines, database policies, object storage, queues, and background jobs
- Change events: grant, update, suspend, revoke, expire, offboard, and transfer ownership
What ships with it
8 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.
- 11d ago First seen · 139 lines · 103 tokens per session scan A a43dbf580d58
review-access-control is a skill published in the GitHub repository Sefyu24/master-iam-skills (7 stars, last pushed 23d ago), licensed MIT. It adds 103 tokens to every session and 1,393 once invoked, about $0.0005 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
configuring-ldap-security-hardening
Harden LDAP directory services against common attacks including credential harvesting, LDAP injection, anonymous binding, and channel binding bypass. Covers LDAPS enforcement, channel binding, LDAP si.
blind-sqli
Blind SQL injection under hostile WAF — manual bypass playbook for when sqlmap fails because common tokens (SUBSTRING, IF, AND, WHERE, single quotes) are filtered. Covers token-fingerprinting probe loops, arithmetic-multiplication boolean evaluation, hex-encoded literals, and exponential-probe binary search. Loaded on…
hpp
HTTP Parameter Pollution — parser discrepancies between proxy/server/app, WAF bypass, auth/ACL bypass, injection delivery.
php-type-juggling
PHP type juggling and magic hash attacks — exploit loose comparison (==) with 0e-prefixed hash collisions and NULL returns to bypass authentication.
verb-tampering
HTTP verb/method tampering — auth bypass via HEAD/OPTIONS/arbitrary methods, X-HTTP-Method-Override, TRACE/PUT/DELETE exposure, framework routing flaws.
csrf
Cross-Site Request Forgery — missing/invalid tokens, method override, JSON CSRF, SameSite gaps, double-submit flaws, login/logout CSRF, and CSRF-via-XSS chains to account takeover.