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 agentmods add skills/fattain-naime/engineering-docs/admin-access-control-specificationnpx skills add fattain-naime/engineering-docs --skill admin-access-control-specificationgit clone --depth 1 https://github.com/fattain-naime/engineering-docsWhat 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 | $0.00075 | $0.03488 |
| Opus 5 | $0.00037 | $0.01744 |
| Sonnet 5 | $0.00015 | $0.00698 |
| Haiku 4.5 | $0.00007 | $0.00349 |
Grade A, and why
admin-access-control-specification 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 2d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Produce an access control specification that defines every privilege level in a system, exactly what each one can and cannot do, how admin actions are logged, and what happens when access is needed outside the normal process.
"If user.is_admin" is not an access control design - it's the absence of one. This document forces every permission to be a deliberate decision, written down once, instead of discovered by testing what an admin account happens to be able to click.
Input
Works best with: The name of the system and the roles that already exist or are anticipated (even informally - "there's regular users and then there's us"). Also valuable: Any compliance requirements (SOC 2, PCI-DSS, GDPR), known sensitive actions (refunds, data export, user impersonation), and whether multiple organizations/tenants share the system.
Example invocation: Define the access control specification for our project-management SaaS. Roles so far: workspace owner, admin, regular member, and a guest role with view-only access. We also have an internal support team that needs to see customer data to help with tickets.
Key Concepts
Role-Based Access Control (RBAC)
Define roles as named bundles of permissions, and assign roles to users - never assign individual permissions directly to a user. This keeps the system auditable: "what can an Admin do" has one answer, not one answer per admin.
Principle of Least Privilege
Every role gets the minimum permissions required for its purpose, not the maximum that seems convenient. A support role that needs to view account data to help with tickets does not also need permission to change billing - even if the same person happens to also hold a role that can.
Permission Matrix
The core artifact: a table of every role against every protected action/resource, with an explicit Allow/Deny for each cell. No cell should be left undecided - an undecided permission becomes a bug (either a silent block or a silent hole) the first time someone hits it.
What ships with it
1 file 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.
- 2d ago First seen · 225 lines · 75 tokens per session scan A 0ae7a20f62e6
admin-access-control-specification is a skill published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 18d ago), licensed MIT. It adds 75 tokens to every session and 3,488 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…