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/product-on-purpose/thinking-framework-skillsWrote 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/product-on-purpose/thinking-framework-skills/think-research-framework)<a href="https://agentmods.dev/commands/product-on-purpose/thinking-framework-skills/think-research-framework"><img src="https://agentmods.dev/badge/commands/product-on-purpose/thinking-framework-skills/think-research-framework.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 | $0.00053 | $0.00223 |
| Opus 5 | $0.00026 | $0.00112 |
| Sonnet 5 | $0.00011 | $0.00045 |
| Haiku 4.5 | $0.00005 | $0.00022 |
Grade A, and why
think-research-framework scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Invoke the think-research-framework skill to research and grade the request.
Input ($ARGUMENTS) is one of:
- A framework name, optionally with a one-line gloss. Run NAME mode: research the method, grade its evidence on the seven-tier model, assess overlap against the shipped catalog, write frameworks//dossier.md, and print a schema-valid PROPOSED registry entry plus a one-screen verdict. Never auto-write the registry.
- A brief of the form "discover N in family ". Run DISCOVERY mode: return a ranked shortlist of candidate methods, each with a one-line mechanism and a distinctness hypothesis. No dossiers, no registry entries.
$ARGUMENTS
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.
- 8d ago First seen · 15 lines · 53 tokens per session scan A 0a86eb3d9a05
think-research-framework is a command published in the GitHub repository product-on-purpose/thinking-framework-skills (14 stars, last pushed 22d ago), licensed Apache-2.0. It adds 53 tokens to every session and 223 once invoked, about $0.0003 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
doff
Doff the current masque and return to baseline Claude.
speckit.polish
Polish and complete speckit workflow — quality gate, docs, changelog, MR.
review
Recent git commits: !git log --oneline -10.
health
Check running Claude Code or Codex sessions, find zombies, offer to clean up safely.
quick
Quick 10-second context health check with quality score and top issues.
session-recap
Summarize recent CHANGELOG.md entries for context restoration. Parses the canonical heading shape ## YYYY-MM-DD — pass-N — summary. Filters: last N (default 10), YYYY-MM date prefix, or "today". Supports --json for machine-readable output.