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/MadeByTokens/claude-code-plugins-madebytokensWrote 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-code-plugins-madebytokens/refine)<a href="https://agentmods.dev/commands/madebytokens/claude-code-plugins-madebytokens/refine"><img src="https://agentmods.dev/badge/commands/madebytokens/claude-code-plugins-madebytokens/refine.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 | $0.00017 | $0.00426 |
| Opus 5 | $0.00009 | $0.00213 |
| Sonnet 5 | $0.00003 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
refine 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.
What it actually says
Refine Current Section
The user wants to iterate on the current section to improve it.
Actions
- Read
.prd-stateto get current section - Read session file to get current content
- Present current content
- Ask what to improve
Display Format
REFINING: [Section Name]
Current content:
───────────────────────────────
[Current section content from file]
───────────────────────────────
Refinement Options
Use AskUserQuestion:
{
"questions": [
{
"question": "What aspect would you like to refine?",
"header": "Refine",
"multiSelect": false,
"options": [
{"label": "Add detail", "description": "Expand with more specific information"},
{"label": "Clarify language", "description": "Make requirements more precise"},
{"label": "Add edge cases", "description": "Consider failure scenarios"},
{"label": "Revise completely", "description": "Start this section fresh"}
]
}
]
}
Refinement Process
Based on selection:
Add detail:
- Ask targeted questions about what's missing
- Propose additions
- Update file with approved changes
Clarify language:
- Identify vague terms ("should", "might", "fast", "easy")
- Propose specific replacements
- Update file with approved changes
Add edge cases:
- Ask "What if X fails?"
- Ask "What happens when Y is empty/null/invalid?"
- Document error scenarios and expected behavior
Revise completely:
- Walk through section from scratch
- Ask all relevant questions again
- Replace section content entirely
Important
- Always show changes before writing to file
- Get explicit approval before updating
- Keep iterating until user is satisfied
- Do NOT write code
- Stay in PRD mode
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 First seen · 80 lines · 17 tokens per session scan A 9b856e063bf7
refine is a command published in the GitHub repository MadeByTokens/claude-code-plugins-madebytokens (2 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 426 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 2026-08-31.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.