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/fstandhartinger/ralph-wiggum/speckit.implementgit clone --depth 1 https://github.com/fstandhartinger/ralph-wiggumWrote 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/fstandhartinger/ralph-wiggum/speckit.implement)<a href="https://agentmods.dev/commands/fstandhartinger/ralph-wiggum/speckit.implement"><img src="https://agentmods.dev/badge/commands/fstandhartinger/ralph-wiggum/speckit.implement.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 | $0.00011 | $0.00630 |
| Opus 5 | $0.00005 | $0.00315 |
| Sonnet 5 | $0.00002 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
speckit.implement 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 5d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Overview
This command launches the Ralph Wiggum implementation loop to process specifications autonomously. The agent iterates until acceptance criteria and Completion Signal requirements pass.
Prerequisites
-
Ralph Wiggum Plugin: Must be installed in Claude Code
/plugin install ralph-loop@claude-plugins-official -
At least one spec: Specs must exist in
specs/with Completion Signal sections -
Context files:
.specify/memory/constitution.md— Project principlesAGENTS.md— Development guidelinesRALPH_PROMPT.md— Master prompt (optional, can use inline)
Execution
Option A: Single Spec
If $ARGUMENTS specifies a single spec (e.g., "001-user-auth"):
/ralph-loop:ralph-loop "Implement the spec $ARGUMENTS from specs/$ARGUMENTS/spec.md.
Context:
- Read .specify/memory/constitution.md for project principles
- Read AGENTS.md for development guidelines
Process:
1. Read and understand the full spec
2. Implement all requirements
3. Complete ALL items in the Completion Signal section
4. Run all tests (unit, integration, browser, visual)
5. Verify no console/network errors
6. Commit and push changes
7. Deploy if required and verify
8. Iterate until all checks pass
Output <promise>DONE</promise> when ALL checks pass." --completion-promise "DONE" --max-iterations 30
Option B: All Specs (Master Loop)
If no specific spec provided, run the master loop:
/ralph-loop:ralph-loop "Work through all specifications in specs/ folder, implementing each one until its acceptance criteria pass, then move to the next.
Context:
- Read .specify/memory/constitution.md for project principles
- Read AGENTS.md for development guidelines
For each spec in numerical order:
1. Read the spec from specs/{spec-name}/spec.md
2. Implement all requirements
3. Complete ALL items in the Completion Signal section
4. Commit, push, and verify deployment
5. Update history if required
6. Move to next spec
Output <promise>ALL_DONE</promise> when all specs complete." --completion-promise "ALL_DONE" --max-iterations 100
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.
- 5d ago First seen · 88 lines · 11 tokens per session scan A c357b3f26ed9
speckit.implement is a command published in the GitHub repository fstandhartinger/ralph-wiggum (292 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 630 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
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.