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/ddunnock/claude-plugins/implementgit clone --depth 1 https://github.com/ddunnock/claude-pluginsWhat 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 | $0.00009 | $0.02705 |
| Opus 5 | $0.00005 | $0.01352 |
| Sonnet 5 | $0.00002 | $0.00541 |
| Haiku 4.5 | $0.00001 | $0.00270 |
Grade B, and why
implement scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/memory/project-status.md How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
Execute tasks from speckit/*-tasks.md with batch execution, gates, and mandatory hooks.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Usage
/implement TASK-001 # Single task
/implement TASK-001..TASK-005 # Range
/implement "Phase 1" # All in phase
/implement @foundation # All with group
/implement --continue # Resume from last
/implement # No argument - triggers status check
MANDATORY: Pre-Execution Hooks
CRITICAL: These hooks MUST execute BEFORE any task implementation begins.
Pre-Hook 1: Load Project Status
ALWAYS read .claude/memory/project-status.md first to understand:
- Current phase and progress
- What was completed in previous sessions
- Any blockers or failed criteria from last run
- Recommended next actions
Read: .claude/memory/project-status.md
Extract:
- Current Phase: [phase name]
- Progress: [X]/[Y] tasks ([Z]%)
- Last Activity: [date] - [what was done]
- Pending Actions: [list]
Pre-Hook 2: Validate Argument / Show Status
IF no argument provided OR invalid argument:
## Current Project Status
| Metric | Value |
|--------|-------|
| Project | Knowledge MCP |
| Current Phase | Phase [N]: [Name] |
| Progress | [X]/[Y] tasks ([Z]%) |
| Last Updated | [DATE] |
### Phase Progress
| Phase | Status | Completed/Total |
|-------|--------|-----------------|
| Phase 1 | ✓ COMPLETE | 6/6 |
| Phase 2 | IN PROGRESS | 3/8 |
| Phase 3 | PENDING | 0/5 |
### Recommended Next Action
Based on current state, you should run:
/implement "Phase 2"
Or to continue from where you left off:
/implement --continue
### Available Selectors
| Selector | What It Does |
|----------|--------------|
| `TASK-XXX` | Execute single task |
| `TASK-XXX..TASK-YYY` | Execute range |
| `"Phase N"` | Execute all in phase |
| `@group` | Execute all with group tag |
| `--continue` | Resume from last position |
| `--all` | Execute all pending tasks |
**Please specify which tasks to implement.**
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 · 437 lines · 9 tokens per session scan B 7688c0a73d7a
implement is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 2,705 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.