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/thibautbaissac/rails_ai_agents/implementgit clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agentsWrote 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/thibautbaissac/rails_ai_agents/implement)<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/implement"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/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 | $0.00025 | $0.00733 |
| Opus 5 | $0.00013 | $0.00367 |
| Sonnet 5 | $0.00005 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
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 4d 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 — 66 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).
Outline
-
Locate feature directory: Run
.specify/scripts/bash/check-prerequisites.sh --json --paths-onlyfrom repo root. Parse JSON for FEATURE_DIR, FEATURE_SPEC, and TASKS paths. For single quotes in args, use escape syntax: e.g 'I'''m Groot' (or double-quote if possible). -
Validate artifacts exist:
- Check that FEATURE_DIR/spec.md exists. If not: "Run
/sdd-change:specifyfirst." - Check that FEATURE_DIR/tasks.md exists. If not: "Run
/sdd-change:tasksfirst."
- Check that FEATURE_DIR/spec.md exists. If not: "Run
-
Load context:
- REQUIRED: Read spec.md (the change spec — Problem, Proposed Change, Acceptance Criteria)
- REQUIRED: Read tasks.md (the flat task list)
- IF EXISTS: Read
.specify/memory/constitution.mdto respect project principles - IF EXISTS: Read
.specify/memory/lessons-learned.md— filter to entries tagged[phase:implement]or[phase:all]and note any relevant to the current change
-
Execute tasks sequentially:
- Parse all uncompleted tasks (
- [ ]items) from tasks.md - For each task:
- Execute the task as described (create, modify, or update files)
- Follow Rails conventions and the project's architecture (skinny controllers, services for business logic, normalization-only callbacks)
- Mark the task as
[X]in tasks.md immediately after completion - Report brief progress: task ID and what was done
- If a task fails:
- Provide clear error context (what failed and why)
- Log the error to
.specify/memory/lessons-learned.mdif it represents a reusable learning (create the file with its standard header if it does not exist) - Halt execution and suggest next steps for manual resolution
- Parse all uncompleted tasks (
-
Final validation:
- Run
bundle exec rspecand report results - Run
bundle exec rubocop -aand report results - If either fails: attempt to fix the issues and re-run (max 2 attempts)
- If still failing after retries: report the remaining issues for manual resolution
- Run
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.
- 4d ago First seen · 66 lines · 25 tokens per session scan A fbef15a7810c
implement is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 733 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
git
Git operations with intelligent commit messages and workflow optimization.
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.