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/davistroy/claude-marketplace/implement-plan.evalgit clone --depth 1 https://github.com/davistroy/claude-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/davistroy/claude-marketplace/implement-plan.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/implement-plan.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/implement-plan.eval.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 | $0.00794 |
| Opus 5 | $0.00000 | $0.00397 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
implement-plan.eval 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 6d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /implement-plan
Purpose
Executes an IMPLEMENTATION_PLAN.md using orchestrated subagents. Each work item is implemented, tested, and committed by a dedicated subagent. Good behavior: items are implemented in order, status markers are updated, tests pass, and a PR is created at the end.
Fixtures
| Fixture | Purpose |
|---|---|
plans/implementation-plan.md |
2-phase, 5-item plan for the standup bot MVP |
Setup
IMPORTANT: This command is destructive and must only be run in an isolated git repository set up for eval purposes. It creates branches, makes commits, and opens a GitHub PR.
git clone <a-test-project-repo> /tmp/eval-implement-plan
cd /tmp/eval-implement-plan
cp <fixtures>/plans/implementation-plan.md IMPLEMENTATION_PLAN.md
git checkout -b eval-test-branch
Test Scenarios
S1: Prerequisite validation — on main branch
Setup: Be on main branch with an IMPLEMENTATION_PLAN.md present.
Invocation: /implement-plan
Must:
- Detects that current branch is main/master
- Displays error: "Cannot run on main/master branch"
- Does not start implementation
S2: Prerequisite validation — plan file missing
Invocation: /implement-plan (no IMPLEMENTATION_PLAN.md in directory)
Must:
- Error message explaining plan file is missing
- Suggests
/plan-improvementsor/create-planto generate it - Does not make any changes
S3: Custom plan path
Setup: Plan file at non-default location.
Invocation: /implement-plan --input fixtures/plans/implementation-plan.md
Must:
- Reads plan from the specified path
- Does not look for IMPLEMENTATION_PLAN.md at repo root
S4: Full execution (integration — run in isolated env)
Setup: Clean feature branch, IMPLEMENTATION_PLAN.md copied to repo root, gh authenticated.
Invocation: /implement-plan
Must:
- Processes items in plan order (1.1 before 1.2, Phase 1 before Phase 2)
- Updates
<!-- STATUS:todo -->to<!-- STATUS:done -->as items complete - Creates a PR at the end (without
--auto-merge) - Does not push directly to main
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.
- 6d ago First seen · 117 lines · 0 tokens per session scan A 44ce1cf2f845
implement-plan.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 794 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.