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/madebytokens/claude-brainstorm/backgit clone --depth 1 https://github.com/MadeByTokens/claude-brainstormWrote 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/madebytokens/claude-brainstorm/back)<a href="https://agentmods.dev/commands/madebytokens/claude-brainstorm/back"><img src="https://agentmods.dev/badge/commands/madebytokens/claude-brainstorm/back.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 | $0.00024 | $0.00406 |
| Opus 5 | $0.00012 | $0.00203 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
back 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- back — 100% identical, 0 lines differ
What it actually says
Return to Parent Thread
The user wants to return from the current fork to its parent thread.
Actions to Perform
-
Update session state:
- Pop the current thread from the stack
- Set current thread to the parent (top of stack)
- Keep the fork in the "open forks" list (it's explored, not deleted)
-
Update session file:
- Add a separator line
--- - Add continuation header:
## [PARENT THREAD] [topic] (continued) - Add return reference:
Returned from: [fork name]
- Add a separator line
-
Acknowledge the return to user:
BACK TO: [parent thread name]
(Explored: [fork name])
[Brief 1-line summary of what was explored in the fork]
Where were we? [Continue the parent thread's brainstorm, or ask what to explore next]
If Already at MAIN
If the user calls /brainstorm:back while already at MAIN (no parent to return to), display:
Already at MAIN thread - no parent to return to.
Current open forks: [list forks if any]
Then use AskUserQuestion to offer options:
{
"questions": [
{
"question": "What would you like to do?",
"header": "Navigate",
"multiSelect": false,
"options": [
{"label": "Fork", "description": "Branch into a new tangent"},
{"label": "Keep exploring", "description": "Continue on the main thread"}
]
}
]
}
Important
- Stay in brainstorming mode
- After returning, continue the parent thread's brainstorm
- Briefly acknowledge what was explored in the fork
- Don't lose momentum - keep generating
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 · 66 lines · 24 tokens per session scan A c169fa1829f2
back is a command published in the GitHub repository MadeByTokens/claude-brainstorm (13 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 406 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 2026-08-30.
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.