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/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/amend-plan)<a href="https://agentmods.dev/commands/closedloop-ai/claude-plugins/amend-plan"><img src="https://agentmods.dev/badge/commands/closedloop-ai/claude-plugins/amend-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 | $0.00013 | $0.03979 |
| Opus 5 | $0.00006 | $0.01989 |
| Sonnet 5 | $0.00003 | $0.00796 |
| Haiku 4.5 | $0.00001 | $0.00398 |
Grade A, and why
amend-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 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.
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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experimental Plan Amend Command
Discuss and apply amendments to a plan.json implementation plan through natural conversation.
Role
When you invoke this command, you are the orchestrator. You handle the conversation directly, making edits when appropriate and using the state management script to persist conversation across workflow runs.
Usage
# With workdir (GitHub workflow passes this via $CLOSEDLOOP_WORKDIR)
/code:amend-plan --workdir .closedloop-ai/work --message "for task T-1.1, don't remove the SplashScreen.setLoadingInfo call"
# Auto-detect from $CLOSEDLOOP_WORKDIR or .closedloop-ai/work
/code:amend-plan --message "change the caching approach in T-2.1"
# With explicit state file
/code:amend-plan --workdir .closedloop-ai/work --state-file .closedloop-ai/work/amend-session.json --message "yes go ahead"
Options
--workdir <path>- Path to the work directory. If not provided, uses$CLOSEDLOOP_WORKDIRenv var or defaults to.closedloop-ai/work--message <text>- The user's message (required)--state-file <path>- Path to amend session state file. Defaults to{workdir}/amend-session.json
Workflow
Use TodoWrite to track your progress through the amendment workflow:
TodoWrite([
{"content": "Setup: Load state, read plan.json, add user message", "status": "pending", "activeForm": "Setting up amendment context"},
{"content": "Analyze user intent (directive, question, or confirmation)", "status": "pending", "activeForm": "Analyzing user intent"},
{"content": "Process request and determine response", "status": "pending", "activeForm": "Processing amendment request"},
{"content": "Save response to state file", "status": "pending", "activeForm": "Saving response to state"},
{"content": "Apply changes if confirmed (edit plan.json, regenerate plan.md, run apply)", "status": "pending", "activeForm": "Applying changes"}
])
Note: The last todo (Apply changes) only applies if the user gave a directive that was safe to apply, or confirmed a previously discussed change. Skip it if you're just answering a question or raising a concern.
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 · 413 lines · 13 tokens per session scan A 5b945614485c
amend-plan is a command published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 3,979 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 2026-09-07.
Other commands, from other repositories
epic-claim
Claim an epic issue, stamp coordination state, and sync local ownership.
epic-decompose
Break an epic into task children without creating task branches.
epic-publish
Publish a validated epic update back to the issue and local cache.
epic-review
Mark epic review requested, approved, or changes requested.
epic-sync
Sync epic issue bodies, labels, and local coordination snapshots from GitHub.
epic-unblock
Sweep blocked epic issues and reopen anything whose dependencies are closed.