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 skills add brunob54/superpowers-orchestrator --skill claude-md-creatorgit clone --depth 1 https://github.com/brunob54/superpowers-orchestratorWrote 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/skills/brunob54/superpowers-orchestrator/claude-md-creator)<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/claude-md-creator"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/claude-md-creator/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/skills/brunob54/superpowers-orchestrator/claude-md-creator"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/claude-md-creator.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 | $0.00088 | $0.01189 |
| Opus 5 | $0.00044 | $0.00594 |
| Sonnet 5 | $0.00018 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
claude-md-creator 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 12d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE / AGENTS Context File Creator
Creates repository-level context files (CLAUDE.md, AGENTS.md) that give coding agents the minimum guidance needed to work correctly in a repo.
Core principle: Only include what the agent cannot easily discover itself.
Empirical research (Gloaguen et al., 2026 — "Evaluating AGENTS.md") shows that LLM-generated context files decrease agent performance by 3% and increase cost by 20-23% when they contain redundant or overly broad content. Human-written, minimal context files improve performance by ~4%. The difference comes down to signal density — every unnecessary line adds cognitive load without helping the agent solve tasks.
Trigger Conditions
Invoke this skill when any of the following occur:
- The
/initcommand is run - The user asks to create, write, or update a
CLAUDE.mdorAGENTS.md - The user mentions "agent context", "initialize project", "set up Claude Code"
- A repo is missing a
CLAUDE.mdand the user begins a new project setup - During
brainstormingorwriting-planswhen the repo lacks a context file
What to Include (highest to lowest priority)
1. Build, test, and lint commands (highest impact)
Explicit tool and command mentions are the single most effective instruction type — agents use mentioned tools 1.6x-2.5x more often. Spell out exact commands:
npm run test -- --watch
uv run pytest tests/ -x
make lint && make typecheck
2. Non-obvious environment setup
Env vars, required services, secrets handling, database setup — things the agent would get wrong without being told.
3. Critical constraints (things that cause wrong behavior if violated)
Focus narrowly on constraints where violating them breaks something:
- "Never edit files in
generated/— they're overwritten by codegen" - "Always run migrations through the ORM, never raw SQL"
- "The
legacy/module uses CommonJS — no ES imports"
4. Repo-specific patterns and anti-patterns
Only patterns unique to this project that differ from standard practice. If it's what any experienced developer would do by default, leave it out.
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.
- 12d ago First seen · 86 lines · 88 tokens per session scan A cf0ea2bbbba4
claude-md-creator is a skill published in the GitHub repository brunob54/superpowers-orchestrator (3 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,189 once invoked, about $0.0004 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 skills, from other repositories
recall-promote
Use when recurring themes need promotion to permanent MEMORY.md entries, or when the user mentions 'promote', 'recurrence', or 'recurring themes'.
progress
Use when the user wants to view their current progress.md file. Also use when the user mentions 'show progress', 'current progress', 'what have we done', or '/tandem:progress'.
memory
Use when the user wants to view their current MEMORY.md file. Also use when the user mentions 'show memory', 'current memory', 'what do we know', or '/tandem:memory'.
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive-mine
Nightly scan of session transcripts -- extract decisions, tasks, people, insights.