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/leanandmean/mach10/issue-creategit clone --depth 1 https://github.com/LeanAndMean/mach10What 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 | $0.00011 | $0.02006 |
| Opus 5 | $0.00005 | $0.01003 |
| Sonnet 5 | $0.00002 | $0.00401 |
| Haiku 4.5 | $0.00001 | $0.00201 |
Grade A, and why
issue-create 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issue
You are creating a structured GitHub issue. This may be invoked at any point in the workflow — to capture deferred review findings, document refactoring needs, or track new feature ideas.
Context (optional): $ARGUMENTS
Step 1: Gather Context
If context was provided ($ARGUMENTS), parse it for two kinds of input and act on each:
- Descriptive content (problem statement, feature description, observed behavior, motivation): Use as the starting point for drafting the issue body in Step 2.
- Meta-directives about the issue itself (e.g., "use the bug template", "tag as priority-high", "assign me", "make this a tracking issue"): Note these for the appropriate downstream step. Template choice steers the template selection later in this step. Labels and assignees are applied via
gh issue create/gh issue editflags in Step 5. Honor meta-directives explicitly -- do not fold them into the issue body as descriptive text.
If no context was provided, ask the user what the issue is about.
Check if the repository has issue templates:
ls .github/ISSUE_TEMPLATE/ 2>/dev/null
If templates exist, read them and select the most appropriate one. If no templates, use the standard format below.
Step 2: Draft the Issue
Draft a structured issue with these sections:
Title
- Clear, concise, actionable (under 80 characters)
- Use imperative form (e.g., "Add validation for bulk solvent inputs")
Body
- Summary: 2-3 sentences describing the problem or feature
- Current Behavior (for bugs/improvements): What happens now
- Proposed Behavior: What should happen -- describe desired outcomes rather than implementation steps. If the issue's subject is a command definition, agent definition, or workflow specification, naming the specific file and section as the target of a behavioral change is appropriate here; move to Technical Notes only when describing the mechanism of the change (algorithm, control flow, data structure choices).
- Acceptance Criteria: Bullet list of verifiable end-state conditions that define "done", independent of implementation approach. Exception: when the artifact being changed is itself a specification (command definitions, config schemas, workflow files, documentation), implementation-specific criteria are appropriate because the spec IS the implementation.
- Context (optional): Links to related PRs, issues, or discussions
- Technical Notes (optional): Implementation hints, relevant files, architectural considerations
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 · 144 lines · 11 tokens per session scan A aadbd7ee8619
issue-create is a command published in the GitHub repository LeanAndMean/mach10 (20 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 2,006 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
psm
/oh-my-claudecode:psm is a compatibility alias for /oh-my-claudecode:project-session-manager.
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.