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.
git clone --depth 1 https://github.com/cicababba/claude-plugins-marketplaceWrote 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/cicababba/claude-plugins-marketplace/run)<a href="https://agentmods.dev/commands/cicababba/claude-plugins-marketplace/run"><img src="https://agentmods.dev/badge/commands/cicababba/claude-plugins-marketplace/run.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 5.1 | $0.00000 | $0.00581 |
| Opus 5 | $0.00000 | $0.00291 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
run 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 8d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run — Execute Development Plan
Execute the next available steps from the active development session.
ABSOLUTE SCOPE & RESTRICTIONS
- This command executes planned steps from
plan.md - It MUST update progress in
session.md - It MUST keep Status as
IN_PROGRESS - It MUST NEVER set Status to
COMPLETED(this is done by/end)
1. Load Active Session
Skill: Use
session-managerto load the current session
- Read
.claude/dev-sessions/.current-session - If empty or missing:
- Filter sessions by Status:
READYorPLANNING - Present filtered list to user
- Let user select one
- Update
.current-sessionwith selection
- Filter sessions by Status:
- Load session and show current status
2. Validate Session State
Skill: Use
artifact-fs-managerto verify artifacts exist
- Check that all required files exist and are readable:
context-analysis.mdspecification.mdplan.mdsession.md
- If
plan.mdis missing:- Suggest running
dev-plan-orchestratorskill first - Exit command
- Suggest running
3. Execute Steps
Skill: Use
dev-execution-orchestratorto run available steps
- Invoke
dev-execution-orchestratorwith:- Session path
- Execution mode:
full-batch(ornext-stepif user prefers)
- The skill will:
- Validate plan integrity (no circular dependencies)
- Set session Status to
IN_PROGRESS - Determine executable steps (dependencies satisfied)
- Dispatch to appropriate sub-agents using pre-generated prompts
- Update step status after each completion
- Update batch status in Execution Batches
- Update Progress counter
4. Report Progress
After execution completes:
- Show summary of executed steps
- Show current progress (X/Y steps completed)
- List any blocked steps and why
- List next executable steps (if any)
- Keep Status as
IN_PROGRESS
IMPORTANT: Do NOT change global session status to COMPLETED
Error Handling
- No active session: Suggest running
/initfirst - Session files missing: Suggest re-initialization or recovery (via skill error handling)
- Step execution fails:
- Mark step as
FAILEDwith reason - Check if failure blocks other steps
- Suggest remediation
- Continue with other executable steps if possible
- Mark step as
- Dependency conflict: Report which steps are blocked and why
- No executable steps: Report current state, keep Status as
IN_PROGRESS
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.
- 8d ago First seen · 86 lines · 0 tokens per session scan A f1bfbdde45a8
run is a command published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 581 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.