Agent skill

Access And Identity

by cbrock84 in cbrock84/headcount

Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process.

MITAuto-check passedBackend & APIs

Install Access And Identity

skills CLI
$ npx skills add cbrock84/headcount --skill access-and-identity -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cbrock84/headcount access-and-identity --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/security/skills/access-and-identity .claude/skills/access-and-identity && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
access-and-identity
GitHub stars
2k
Token cost
~1.1k tokens
SKILL.md length
628 words
Files
2 (incl. references)
Skills in repo
178
Repo updated
First seen
Licence
MIT

At a glance

Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process.

  • Tasks that involve Authentication
  • SKILL.md covers Principles that actually hold, Authentication, Joiner, mover, leaver and Service and machine credentials, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Access reviews and audit trails

What it does

Access And Identity is an agent skill from cbrock84/headcount. Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Use this to design a permissions model, run an access review, reduce standing privilege, handle offboarding, set up SSO or MFA, manage service and machine credentials, or diagnose why permissions have sprawled.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/sources.md`).

It sits in Backend & APIs, covering Authentication, Access reviews and audit trails and Authorization and RBAC. The repository describes itself as: An agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs… The licence is MIT.

When your agent uses it

  • Tasks that involve Authentication
  • Tasks that involve Access reviews and audit trails
  • Tasks that involve Authorization and RBAC

Example prompts

  • “Use the access-and-identity skill to design and audits who can reach what — authentication, authorization models, privileged access, service…”
  • “/access-and-identity”

What it can do on your machine

Read from SKILL.md and the folder at commit 98d1c17. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Access And Identity loads about 1.1k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 628 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cbrock84/headcount at commit 98d1c17, republished under its MIT licence (© cbrock84). 628 words, ~1,143 tokens.

Download SKILL.mdSave it as .claude/skills/access-and-identity/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
access-and-identity
description
Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Use this to design a permissions model, run an access review, reduce standing privilege, handle offboarding, set up SSO or MFA, manage service and machine credentials, or diagnose why permissions have sprawled.

Access and identity

Access accumulates. People change roles and keep the old permissions, services get broad credentials because narrow ones were inconvenient, and contractors' accounts outlive their contracts. Left alone, entitlement always grows and never shrinks.

Principles that actually hold

  • Least privilege, and it must be practical. A model so restrictive that people share accounts to get work done is worse than a looser one they follow.
  • Role-based, not person-based. Grants attached to individuals are ungovernable at any scale.
  • Time-bound elevation over standing privilege. Nobody should hold administrative access continuously because they occasionally need it. Elevation on request, with a reason, expiring automatically.
  • Separate duties where the consequence is severe. The person who requests a payment does not approve it; the person who writes the deploy does not solely authorize the production change.

Authentication

Single sign-on wherever possible — the value is not convenience, it is that offboarding becomes one action rather than forty. Every system outside SSO is a system someone will still have access to after they leave.

Multi-factor everywhere it is available, and phishing-resistant factors for administrative access. SMS is better than nothing and is the weakest option worth deploying.

Joiner, mover, leaver

Mover is the one everyone gets wrong. Joining and leaving are events with a process; changing role usually adds permissions and removes none, which is how a long-tenured employee ends up with access to everything.

Make role change a revoke-and-regrant rather than an addition. It is the single highest-value change most organizations can make to their access posture.

Offboarding needs to be same-day, cover everything including systems outside SSO, and be verified rather than assumed. Keep a list of what exists to be revoked — the fastest way to find the shadow systems is to try to offboard someone thoroughly.

Service and machine credentials

Usually more numerous and less governed than human ones. Each needs a named human owner, a scope limited to its actual use, a rotation path, and an expiry.

Prefer short-lived, automatically issued credentials over long-lived keys. A key that never expires will eventually appear in a repository, a log, or a support ticket.

Show full SKILL.md (277 more words)Show less

Access reviews

Periodic, by system, with the reviewer being the person accountable for the data rather than IT. Reviewers who cannot say why someone needs access should remove it — the burden belongs on retention, not removal.

Review dormant accounts as a separate pass. An account nobody has used in six months is either unnecessary or belongs to someone who left.

Diagnosing sprawl

Look for: permissions granted to individuals rather than roles, roles nobody can define, standing administrative access, accounts whose owner has left, service credentials with no owner, and systems outside SSO. Each is a specific fix, and the list is nearly always the same list.

Sources

references/sources.md in this skill lists the outside authorities that settle the questions here — what each one is authoritative for, and what you may do with it. Check them before answering on anything they cover, and cite what you used. Most are free to read and not free to reproduce; the use note on each is binding.

Tooling

Identity providers: Okta, Microsoft Entra ID, Google Workspace, JumpCloud, and similar.

Privileged access and secrets: CyberArk, HashiCorp Vault, 1Password, Doppler, and similar.

Access reviews and provisioning: Okta Identity Governance, Entra ID Governance, Lumos, ConductorOne, and similar. Worth buying at the point a manual quarterly review stops finishing rather than the point it gets tedious.

Never

  • Grant standing access where time-bound access would do the same job.
  • Leave an account active while an offboarding ticket works its way through. Cut access first, reconcile after.
  • Share a credential between people. If two people can use it, no log tells you which one did.
  • Approve your own access request, or review a group you belong to.

© cbrock84, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/security/skills/access-and-identity of cbrock84/headcount.

  • SKILL.md
  • references/sources.md

Open the folder on GitHubat commit 98d1c17

Compare with similar skills

Access And Identity next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Access And Identity compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Access And Identity this skillcbrock84/headcount2k—~1.1kAutomated safety check: PassMIT
Cognitoitsmostafa/aws-agent-skills1.2k1 repos~2.3kAutomated safety check: PassMIT
Django Access Reviewgetsentry/skills1k3 repos~2.6kAutomated safety check: NotesApache-2.0
Auth Implementation Patternsynulihao/AgentSkillOS61810 repos~4.4kAutomated safety check: PassNone
Configuration Cryptogreenpau/caddy-security2.3k—~3.5kAutomated safety check: PassApache-2.0
Supercheck Security Authsupercheck-io/supercheck215—~1.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Cognito

    itsmostafa/aws-agent-skills

    AWS Cognito user authentication and authorization service. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub starsUsed in 1 repo~2.3k tokens
    Backend & APIsAuto-check passed
  • Django Access Review

    getsentry/skills

    Official

    Django access control and IDOR security review. An agent skill from getsentry/skills.

    1k GitHub starsUsed in 3 repos~2.6k tokens
    Backend & APIsAuto-check: notes
  • Auth Implementation Patterns

    ynulihao/AgentSkillOS

    Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems.

    618 GitHub starsUsed in 10 repos~4.4k tokens
    Backend & APIsAuto-check passed
  • Configuration Crypto

    greenpau/caddy-security

    Configure portal/policy JWT keys, token names and lifetimes, key loading and generation, public-key discovery, and System API encryption keys.

    2.3k GitHub stars~3.5k tokensUpdated 5 days ago
    Backend & APIsAuto-check passed
  • Supercheck Security Auth

    supercheck-io/supercheck

    Work on Supercheck authentication, RBAC, tenant isolation, sessions, API and trigger keys, invitations, project membership, project variables, OAuth, super-admin behavior, SSRF, or…

    215 GitHub stars~1.2k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Bkend Auth

    ww-w-ai/bkit-claude-code

    bkend.ai authentication — email/social login, JWT tokens, RBAC, session management.

    601 GitHub stars~937 tokensUpdated 13 days ago
    Backend & APIsAuto-check: notes

More from cbrock84/headcount

All 178 skills in this repo
  • Agent Hierarchy

    cbrock84/headcount

    Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a…

    2k GitHub stars~1.2k tokensUpdated 23 days ago
    Auto-check passed
  • Account Based Marketing

    cbrock84/headcount

    Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group…

    2k GitHub stars~1.2k tokensUpdated 23 days ago
    Auto-check passed
  • Activation

    cbrock84/headcount

    Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account.

    2k GitHub stars~865 tokensUpdated 23 days ago
    Auto-check passed
  • AI ML Governance

    cbrock84/headcount

    Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire.

    2k GitHub stars~1k tokensUpdated 23 days ago
    Auto-check passed
  • AI Research Analyst

    cbrock84/headcount

    Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit.

    2k GitHub stars~916 tokensUpdated 23 days ago
    Auto-check passed
  • AI Search Optimization

    cbrock84/headcount

    Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf.

    2k GitHub stars~829 tokensUpdated 23 days ago
    Auto-check passed

Categories

Questions about Access And Identity

What does Access And Identity do?

Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Access And Identity is an agent skill from cbrock84/headcount. Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process.

When should I use Access And Identity?

Access And Identity fits situations like: tasks that involve Authentication; tasks that involve Access reviews and audit trails; tasks that involve Authorization and RBAC.

How do I install Access And Identity in Claude Code?

Run `npx skills add cbrock84/headcount --skill access-and-identity -a claude-code`. Or copy the skill folder (plugins/security/skills/access-and-identity in cbrock84/headcount) into .claude/skills/access-and-identity in your project. Claude Code loads it when a task matches its description.

How do I install Access And Identity in Codex?

Run `npx skills add cbrock84/headcount --skill access-and-identity -a codex`. Or copy the skill folder (plugins/security/skills/access-and-identity in cbrock84/headcount) into .agents/skills/access-and-identity in your project. Codex loads it when a task matches its description.

Can I use Access And Identity in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cbrock84/headcount --skill access-and-identity -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/access-and-identity, .gemini/skills/access-and-identity, .github/skills/access-and-identity and .opencode/skills/access-and-identity in your project.

What does Access And Identity need to run?

SKILL.md names no scripts, command-line tools or credentials: Access And Identity is instructions for the agent only.

Does Access And Identity access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Access And Identity safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Access And Identity use?

Access And Identity is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Access And Identity use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 331 tokens, read only when the agent opens those files.

What are the alternatives to Access And Identity?

Skills that share tags, products or a category with Access And Identity: Cognito (itsmostafa/aws-agent-skills, 1.2k stars), Django Access Review (getsentry/skills, 1k stars), Auth Implementation Patterns (ynulihao/AgentSkillOS, 618 stars) and Configuration Crypto (greenpau/caddy-security, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Access And Identity?

cbrock84 (a GitHub user) maintains it in cbrock84/headcount, which has 2,022 GitHub stars. The repository holds 178 skills in this directory. The repository was last updated on September 17, 2026.

Source: cbrock84/headcount on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.