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/source-code-management/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/source-code-management)<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/source-code-management"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/source-code-management/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/source-code-management"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/source-code-management.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 | $0.00044 | $0.02748 |
| Opus 5 | $0.00022 | $0.01374 |
| Sonnet 5 | $0.00009 | $0.00550 |
| Haiku 4.5 | $0.00004 | $0.00275 |
Grade A, and why
source-code-management 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Code Management
Change Inspection
Inspect status, staged diff, and unstaged diff separately. Never change the index unless asked. Default a commit-message request to staged changes when the index is nonempty and state which unstaged changes are excluded. If the index is empty, describe the working-tree changes and say they must be staged before committing.
Commit Message Rules
All commits must have a proper commit message.
A hand-written commit message subject line must conform to the following rules:
- The first line of each commit message is the subject.
- The subject line MUST be less than 87 characters long.
- The subject line MUST NOT terminate with a period (
.). - The subject line MUST start with a change indicator followed by a colon (
:).
Change Indicators
This repository uses change indicators as package and subsystem labels, plus a small set of maintenance labels. Prefer the most specific AuthCrunch package, CLI, provider, store, or runtime surface when the change is clearly anchored in one component. Use a maintenance label when the change is repository plumbing, documentation, tests, release work, or a deliberately cross-cutting fix.
Selection rules:
- Use exactly one indicator. Do not combine indicators or add parenthesized scopes.
- Prefer names that match repository packages, CLI names, or externally visible
AuthCrunch concepts. For example, use
authn,authz,oauth,ldap,kms, orauthdbctlwhen a change is anchored there. - Use
configonly for top-levelauthcrunch.Config,Serverwiring, cross-surface validation, reload plumbing, or shared config exposure. For package-local config parsing, use the package indicator. - Use
authnfor authentication portal behavior and portal API or HTTP handlers. Useuifor embedded portal/profile UI assets, templates, static assets, icons, profile UI bundles, and UI-specific serving behavior. Usecookiefor cookie-specific issuing, reading, deletion, domain, and name config, even when the code lives underpkg/authn/cookie. - Use
authzfor authorization gatekeepers and policies. Useaclwhen the change is really the shared ACL engine, andauthproxywhen it is remote/basic/API-key auth proxy configuration or authenticators. - Use
idpandidsfor shared identity provider or identity store config, interfaces, and dispatch. Useoauth,saml,ldap, orlocalwhen the change is specific to that provider or store implementation. - Use
identityfor identity and user data models, local user database records, roles, passwords, MFA tokens, API keys, WebAuthn/U2F/GPG/SSH keys, lockouts, QR codes, andpkg/user. - Use
registryfor user registration providers, local registry behavior, and domain restriction rules. - Use
kmsfor crypto keys, keystores, token encryption/decryption, and crypto config parsing. Usesystemfor system API protocol messages, request parsing, generated keys, and system API auth messages. - Use
redirects,authchal,credentials,messaging,translate,waf,apiauth,errors,requests,shared,tagging, orutilwhen the primary change is in that package or its testdata. - Use
authdbctlfor the CLI undercmd/authdbctl, including its README, config, commands, output, and command behavior. Usebuildonly when build output or Makefile build behavior changes. - Use
breakfixfor a reported break-fix issue, regression, panic, or shipped behavior that is visibly broken for users. Usefixfor narrower correctness fixes that are not tied to known user breakage. - Use
securityfor vulnerability fixes, hardening, dependency-audit work, or disclosure-policy changes. If a security fix is tightly scoped to one runtime surface, prefer the surface only when the issue is being handled as ordinary correctness rather than as a vulnerability. - Use
tests, notunittest, for Go tests, fixtures, golden data,testdata, and coverage-only changes. If tests accompany a product change, choose the product indicator instead. - Use
skillsfor AI agent skills, skill metadata, or agent-facing repository instructions. Prefer it overdocsoropswhen the primary purpose is helping AI agents work with this repository. - Use
opsfor dependency, Go toolchain, generated license/version metadata, release, or repository maintenance changes. Usegithubfor GitHub Actions, issue templates, CLA workflow/assets, Funding metadata, or other GitHub repository metadata. - Automated patch and minor releases use
ops: released v<VERSION>. Userelease-and-versioningfor the release workflow. Hand-written release workflow changes also useops. - Use
variousonly when a commit intentionally spans unrelated surfaces and no more specific indicator is honest. - Normalize older repository labels when creating new messages: use
featforfeature,fixorbreakfixforbug/bugfix,authdbctlforcmdchanges to the CLI,githubforclabot/workflow metadata, and a specific package indicator instead ofauth,api,hosting,misc, orchore. - Use colon form for new dependency bumps, such as
ops: upgrade golang.org/x/crypto to v0.48.0, even though older history has subjects without a change indicator.
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 · 255 lines · 44 tokens per session scan A 18b5afd1f68d
source-code-management is a skill published in the GitHub repository greenpau/go-authcrunch (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 2,748 once invoked, about $0.0002 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.