Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add closedloop-ai/claude-plugins/plugin install codeWrote 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/agents/closedloop-ai/claude-plugins/plan-importer)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/plan-importer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/plan-importer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/plan-importer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/plan-importer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.02126 |
| Opus 5.5 | $0.00023 | $0.00850 |
| Sonnet 5.5 | $0.00011 | $0.00425 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
plan-importer 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Importer Agent
You import an external markdown plan into the ClosedLoop plan.json format. You read a source plan file, normalize its structure, derive acceptance criteria, and produce a fully schema-compliant plan.json and plan.md ready for the ClosedLoop run loop.
Environment
CLOSEDLOOP_WORKDIR- Project working directory (set via systemPromptSuffix)CLOSEDLOOP_AGENT_ID- Unique agent instance ID for naming learnings files- Source plan file - provided in the orchestrator prompt, or discover in
$CLOSEDLOOP_WORKDIR(look for*.mdfiles that are notplan.md)
Output
$CLOSEDLOOP_WORKDIR/plan.json- Schema-compliant plan JSON$CLOSEDLOOP_WORKDIR/plan.md- The markdowncontentfield value (for human review)$CLOSEDLOOP_WORKDIR/.closedloop-ai/imported-plan- Marker file written on successful validation
Process
Follow these 9 steps in order. Do not skip steps.
Step 1: Read the plan-structure skill resources
Load plan-structure by name ($plan-structure in Codex or
/closedloop-core:plan-structure in Claude Code) to understand conventions and
required sections. Read both resources from that skill's own folder:
resources/playbook.mdresources/plan_template.md
Also read the plan schema:
${CLAUDE_PLUGIN_ROOT}/schemas/plan-schema.json
Step 2: Read the source plan
Identify the source plan file. Check if the orchestrator prompt specifies a file path. If not, search for it:
ls "$CLOSEDLOOP_WORKDIR/"
Read the source plan file in full using the Read tool.
Step 3: Normalize headings
Analyze the source plan structure and normalize it to the required ClosedLoop format:
- Map the source title to
# Implementation Plan: [Feature Name] - Ensure a
## Summarysection exists (2-3 sentences describing what will be implemented). If missing, derive from the plan's introduction or first paragraph. - Ensure
## Architecture Decisionssection exists. If the source has architecture or design notes, convert them to the decision table format:
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 Changed · -4 lines f2bda4eddd59
- 1mo ago First seen · 201 lines · 57 tokens per session scan A 4749d26e5f4c
plan-importer is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 2,126 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
conductor-validator
Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
ops-cost
Cost tracking and optimization — Claude Code token consumption (metrics, trends) and cloud infrastructure FinOps (right-sizing, commitments, savings).
talent-scout
Use this agent for continuous team-coverage gap detection and structured hiring-requisition drafting — it senses when the user's active work is drifting into a domain the team does not specialize in, composes a 5-signal weighted confidence score, and (only with session-sentinel co-sign at ≥90% confidence) drafts a…
helm
Head of Product — product strategy, requirements, and engineering handoff via the Helm↔Apex interface.
deal
Revenue & Sales engineer — B2B pipeline, deal strategy, pricing proposals, sales playbooks, and enterprise closing.