Borrowing it
Nothing to install: this file belongs to 1cFE/fusion-tea. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/1cFE/fusion-tea/main/.claude/commands/manage-concept.mdgit clone --depth 1 https://github.com/1cFE/fusion-teaWrote 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/1cfe/fusion-tea/manage-concept)<a href="https://agentmods.dev/commands/1cfe/fusion-tea/manage-concept"><img src="https://agentmods.dev/badge/commands/1cfe/fusion-tea/manage-concept/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/commands/1cfe/fusion-tea/manage-concept"><img src="https://agentmods.dev/badge/commands/1cfe/fusion-tea/manage-concept.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 | $0.00014 | $0.04105 |
| Opus 5.5 | $0.00006 | $0.01642 |
| Sonnet 5.5 | $0.00003 | $0.00821 |
| Haiku 4.5 | $0.00001 | $0.00411 |
Grade A, and why
manage-concept 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 2mo 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Concept
Purpose: Open an interactive session for vetting, questioning, and improving a specific concept's analysis. Adapt focus to pipeline state, produce structured outputs (review decisions, memory entries) that integrate with the existing analysis pipeline.
Input: Concept ID or partial ID as $ARGUMENTS (e.g., 11, 11-magnetic-mirror)
Output: Review.md edits, memory entries — all in the concept's analysis directory or shared memory
You are an interactive analysis manager for fusion concept $ARGUMENTS. Your job is to help a human reviewer interrogate the analysis, challenge assumptions, compare against other concepts, and drive improvements — all within a structured session that produces traceable outputs.
Reference Documentation
Before doing anything else, read these two files to understand the pipeline architecture, data structures, and operator workflows:
exploration/concept_analysis/README.md— Pipeline architecture, state detection logic, command reference, data structures (verdict.json, frontmatter fields, LoopState), prompt templates, directory layouts, feedback format contractexploration/concept_analysis/OPERATOR_GUIDE.md— Operator workflows, decision points, common scenarios, troubleshooting
These are the source of truth for how the pipeline works. If anything in this command file contradicts them, the README/OPERATOR_GUIDE win.
When uncertain about pipeline behavior (e.g., what a flag does, how state transitions work, what a command produces), do NOT guess — use the Agent tool (subagent_type: Explore) to investigate the actual code in exploration/concept_analysis/scripts/. Key files:
run_analysis.py— CLI dispatch, command handlerslib/state.py— state detection, staleness propagationlib/loop.py— stage 1 loop runner, feedback-producer selectionlib/iteration.py— IterationState, LoopState, verdict I/Olib/concepts.py— concept resolution, costingfe mappingslib/sources.py— source discovery, PA-N parsinglib/memory.py— reuse pool, exemplars, cross-concept memory
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.
- 2mo ago First seen · 383 lines · 14 tokens per session scan A eced5b58e0c1
manage-concept is a command published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 4,105 once invoked, about $0.0001 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 2026-08-31.
manage-concept compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| manage-concept1cFE/fusion-tea | Command | 5 | 24d ago | MIT | A | 14 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |