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/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)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/implement-plan"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/implement-plan.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 | $0.00019 | $0.12124 |
| Opus 5 | $0.00010 | $0.06062 |
| Sonnet 5 | $0.00004 | $0.02425 |
| Haiku 4.5 | $0.00002 | $0.01212 |
Grade A, and why
implement-plan 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 7d 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 — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan Command
Execute an IMPLEMENTATION_PLAN.md file by orchestrating subagents in a loop. Each work item is implemented, tested, documented, and committed by dedicated subagents while the main agent retains only minimal state — preserving context window capacity for long-running plans.
Input Validation
Optional Arguments:
| Argument | Default | Description |
|---|---|---|
--input <path> |
IMPLEMENTATION_PLAN.md |
Plan file path (absolute or relative to repo root). Use when the plan lives at a non-default location. |
--auto-merge |
false |
Merge the PR and clean up the branch after all items complete. Without it, the command creates the PR and stops. |
--pause-between-phases |
false |
Pause and ask for confirmation before starting each new phase. |
--progress |
false |
Update PROGRESS.md even if absent. By default PROGRESS.md is touched only if it already exists (avoids duplicating git log). |
Argument Resolution: If --input <path> was provided, use it (relative paths resolve against the repository root); otherwise default to IMPLEMENTATION_PLAN.md in the repository root. Store the result as PLAN_FILE and use it for ALL plan-file references below.
Prerequisites Validation: verify that PLAN_FILE exists at the resolved path; the current branch is NOT main or master; the working directory is clean (no uncommitted changes); and GitHub CLI (gh) is authenticated.
If the plan file is missing: output an error stating [PLAN_FILE] was not found, and suggest /plan-improvements (generate from codebase analysis), /create-plan (generate from requirements documents), or a custom path via /implement-plan --input <path-to-plan>; then stop.
If on main/master: output an error that the command cannot run on main/master, and instruct the user to create a feature branch first (git checkout -b feature/implementation); then stop.
If working directory is dirty: check if .implement-plan-state.json exists and contains an "in_progress" or "in_progress_batch" field.
- If so (dirty state likely from an interrupted implementation session): present three options — (1) commit these changes and resume (as
"[X.Y] interrupted work"), (2) stash these changes and resume, (3) abort to inspect manually first. Wait for the user's choice and execute accordingly before proceeding. - If not (no state file or no IN_PROGRESS item): output the standard error that uncommitted changes must be committed or stashed before running the command; then stop.
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.
- 7d ago First seen · 521 lines · 19 tokens per session scan A a48c1120ccf7
implement-plan is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 12,124 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.