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 commands/jhlee111/ash_grant/prgit clone --depth 1 https://github.com/jhlee111/ash_grantWrote 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/commands/jhlee111/ash_grant/pr)<a href="https://agentmods.dev/commands/jhlee111/ash_grant/pr"><img src="https://agentmods.dev/badge/commands/jhlee111/ash_grant/pr.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00750 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
pr 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR
End-to-end workflow: verify code, check docs, commit, push, create PR. Run this after implementation is done and tests pass locally.
Input
$ARGUMENTS — short description of changes (used for branch name and PR title)
Steps
1. Code verification
Run all four checks in parallel. ALL must pass before proceeding:
mix compile --warnings-as-errors
mix test
mix credo
mix format --check-formatted
If any fail, fix the issue and re-run. Do not skip.
2. Analyze changes
Run git diff HEAD and git status to understand what changed.
Categorize changes:
- New modules added?
- Public API changed? (new functions, changed signatures, removed functions)
- New DSL options or entities?
- New behaviours or protocols?
- Config/dependency changes?
3. Documentation gate
Based on the change analysis, check EACH of these. Ask the user for confirmation before proceeding if any are needed:
@moduledoc / @doc:
- Every NEW public module has
@moduledoc - Every NEW public function has
@doc - Changed function signatures: is
@docstill accurate?
README.md:
- New feature → needs section or mention in README?
- New DSL option → DSL Configuration table needs update?
- Changed API → Quick Start / examples still correct?
- Version in Installation section current?
CLAUDE.md:
- New module → Architecture section needs update?
- New command or workflow → Common Commands needs update?
- New test pattern → Test Structure needs update?
usage-rules.md:
- This file is the AI-agent-facing rulebook consumers of AshGrant follow — treat it with the same seriousness as README.
- New DSL option or entity → add to the DSL Configuration table / new section?
- New recommended pattern → add as a "DO:" rule?
- Deprecated or removed option → add as a "DON'T:" rule and update any examples still using it?
- Changed behaviour for an existing rule → update the rule's example and explanation?
guides/*.md:
- New feature has a dedicated guide → add cross-links from every other guide whose topic touches it (audit
grep -l "<new-feature>" guides/and check omissions as deliberately as inclusions). - Pattern was recommended-against → ensure the old-pattern guide text reflects the new recommendation.
- Examples in existing guides still compile / make sense after the change?
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.
- 3d ago First seen · 107 lines · 0 tokens per session scan A b9208c2e0917
pr is a command published in the GitHub repository jhlee111/ash_grant (17 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 750 tokens. 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 2026-09-01.
Other commands, from other repositories
cr
When user uses /cr slash command, review uncommitted code changes with reusable language-aware rules, preferring project-local review commands or rules when they exist.
commit
智能创建 git 提交，分析代码变更并生成符合项目规范的提交信息.
pr-review
Review the current branch changes and suggest PR content.
changelog
Summarize staged git changes into a concise changelog/commit message.
push
Push code, automatically run /commit if not yet committed, compute elapsed time and log work to Jira accurately. Handles all edge cases: no-ticket, no-state, re-push, multi-task, duplicate worklog, corrupt state, negative elapsed, wrong commit author.
merge
Merge branches with auto-generated Conventional Commits message.