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 tobihagemann/turbo --skill recall-rationalegit clone --depth 1 https://github.com/tobihagemann/turboWrote 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/tobihagemann/turbo/recall-rationale)<a href="https://agentmods.dev/skills/tobihagemann/turbo/recall-rationale"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/recall-rationale/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/tobihagemann/turbo/recall-rationale"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/recall-rationale.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 | $0.00074 | $0.01208 |
| Opus 5.5 | $0.00030 | $0.00483 |
| Sonnet 5.5 | $0.00015 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
recall-rationale 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 13d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall Rationale
Locate the Claude Code transcript that produced a given change and recover why it was made. Useful for answering reviewer questions, writing post-hoc explanations, or recovering forgotten context.
Inputs
Accept any of:
- A commit SHA
- A file path, optionally with a line number (
<path>:<line>) - A reviewer question plus surrounding context (file and line)
- A passage with no commit behind it, because the project is not a git repository or the change is uncommitted
If only a file is given, git blame resolves the commit that last touched the line.
Step 1: Resolve the Commit and Run the Script
Call scripts/find_transcript.py with either --commit <sha> or --file <path>[:<line>]. Pass --cwd /path/to/repo when searching a different repo than the current working directory.
python3 <skill-dir>/scripts/find_transcript.py --file <path>:<line>
python3 <skill-dir>/scripts/find_transcript.py --commit <sha>
When there is no commit to resolve, because the project is not a git repository or --file returns no-commit for an uncommitted line, run --phrase with a distinctive stretch of the passage's current text, taken from a single line, instead. It skips git, ranks the project's transcripts by how often they handle the phrase, and returns the same JSON with commit: null.
python3 <skill-dir>/scripts/find_transcript.py --phrase "<distinctive text from the passage>"
With --commit or --file, the script:
- Resolves the commit via
git rev-parseorgit blame - Enumerates directories under the effective Claude configuration home's
projects/tree and filters their transcripts by authoritativecwdrecords, covering path encoding, truncation, collisions, and subdirectory launches - Ranks candidate transcripts whose mtime is within
--window-daysof the commit (default 14) - Scores candidates by mentions of touched files and tool-use edits on them
- Extracts cleaned user prompts and substantive assistant text from the top candidates
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 101 lines · 74 tokens per session scan A b28ff039491a
recall-rationale is a skill published in the GitHub repository tobihagemann/turbo (409 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,208 once invoked, about $0.0003 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 2026-10-01.
Other skills, from other repositories
iterate
Diverge-converge workflow: spin up N agents on isolated worktrees, each exploring a different approach to the same problem. Compare results side-by-side (with optional preview ports), pick a winner, merge it back. Use when the user says /iterate, 'try multiple approaches', 'explore different directions', or wants to…
end
Close a work session — log what happened, update state and the decision log, propose durable memory updates, and check for uncommitted or unpushed work.
diffler
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
napkin
Maintain a per-repo napkin as a continuously curated runbook (not a session log). Activates EVERY session. Read and curate it before work, keep only recurring high-value guidance, organize by priority-sorted categories, and cap each category at top 10 items. The napkin lives at .claude/napkin.md.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.