Borrowing it
Nothing to install: this file belongs to greenpau/go-authcrunch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenpau/go-authcrunch/main/.codex/skills/coding-directives/SKILL.mdgit clone --depth 1 https://github.com/greenpau/go-authcrunchWrote 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/greenpau/go-authcrunch/coding-directives)<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/coding-directives"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/coding-directives/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/greenpau/go-authcrunch/coding-directives"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/coding-directives.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 | $0.00096 | $0.02425 |
| Opus 5 | $0.00048 | $0.01213 |
| Sonnet 5 | $0.00019 | $0.00485 |
| Haiku 4.5 | $0.00010 | $0.00243 |
Grade A, and why
coding-directives 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 yesterday.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Directives
Overview
Apply these directives when editing or reviewing go-authcrunch code. Prefer
small, package-local changes that preserve AuthCrunch's existing runtime shape:
top-level authcrunch.Config and Server wire package-owned configs,
constructors, validators, providers, stores, portals, gatekeepers, registries,
and crypto key stores.
Use the repo-local testing-and-ci skill for every Go code change and when
choosing, adding, or running tests. Use scripts-and-automation for Makefile
targets, generated assets, dependency commands, and release/version workflows. Use
refresh-token-implementation and its identity/transport owners when changing
portal refresh behavior; use release-and-versioning for version invariants.
Use authentication-portal-themes for custom portal templates, branding assets,
and their UI configuration and template contracts.
Use oauth-identity-provider for upstream
OAuth/OIDC token trust, key ingestion and refresh, and provider configuration.
Use authentication-portal-jwks for
portal public signing-key discovery, opt-in admin private-key export, issuer
selection, and JWK serialization.
Use local-password-authentication
for local-store password verification and bcrypt work equalization.
Use authentication-portal-oidc for the
portal acting as a downstream OpenID Provider, including client registration,
authorization grants, consent, dedicated keys, and conformance.
Use authentication-client for reusable portal login clients and CLI credential
handling. Use authdbctl for CLI commands, terminal behavior, and executable E2E
tests.
Package Boundaries
Put behavior in the package that owns the AuthCrunch surface:
pkg/authn: authentication portals, portal HTTP/API handlers, sessions, cookies, MFA/WebAuthn/TOTP/GPG/SSH/API-key profile operations, UI serving, and portal-specific config.pkg/authz: authorization gatekeepers, access policy config, token validators, bypass rules, auth redirects, header injection, and auth proxy integration.pkg/idsandpkg/idp: shared dispatch config and interfaces for identity stores and identity providers. Put provider-specific behavior inpkg/ids/local,pkg/ids/ldap,pkg/idp/oauth, orpkg/idp/saml.pkg/sso,pkg/kms,pkg/registry,pkg/messaging,pkg/identity,pkg/user,pkg/translate, and focused utility packages own their own parsing, validation, models, and tests.pkg/oidcowns the reusable OpenID Provider, public configuration, identity verifier interface, protocol handlers, and browser-session lifecycle. Portal identity, sandbox, and refresh adapters remain inpkg/authn.pkg/authclientowns the JSON portal login client, challenge orchestration, opaque credential results, and optional token-file persistence. It uses the login endpoint without depending on the admin API or a CLI framework.cmd/authdbctlowns configuration discovery, application paths, flags, terminal prompts, database commands, management request retries, and output.
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.
- yesterday First seen · 244 lines · 96 tokens per session scan A 372743463eec
coding-directives is a skill published in the GitHub repository greenpau/go-authcrunch (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 96 tokens to every session and 2,425 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 2026-09-13.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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"…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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…