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/gf-labs/claude-toolbox/pingit clone --depth 1 https://github.com/gf-labs/claude-toolboxWrote 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/gf-labs/claude-toolbox/pin)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/pin"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/pin.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 | $0.00000 | $0.02688 |
| Opus 5 | $0.00000 | $0.01344 |
| Sonnet 5 | $0.00000 | $0.00538 |
| Haiku 4.5 | $0.00000 | $0.00269 |
Grade A, and why
pin 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 5d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collect context
Run this once — it derives scope once, reads the session JSONL once, and emits every section pin needs in a single pass:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-pin.py
Output is delimited by === SECTION === markers. Read the values from each:
| Section | Fields |
|---|---|
SCOPE |
MODE, PROJECT_KEY, PROJECT_DIR, REPO, TW_PROJECT, DATE |
SESSION |
SESSION (id), TITLE, FILES_TOUCHED, CROSS_PROJECT_FILES, BASH_COMMANDS |
GIT |
BRANCH, CHANGES, GIT_LOG, GIT_DIFF_STAT |
BACKLOG |
IN_PROGRESS, UP_NEXT (TaskWarrior) |
STATUS |
LAST_SNAPSHOT, SESSIONS_SINCE, LAST_SESSION_LOG, LOG_ENTRIES |
SESSION_LOG |
PATH, REPEAT_PIN (+ next header suffix), LAST_ENTRY, SAME_SESSION_ENTRIES |
MEMORY |
PATH, LINES, MIGRATION / MIGRATION_NEEDED, CONTENT (full) or TAIL (only if very large) |
PLANS |
plan inventory (or NONE) |
PLUGIN_DRIFT |
plugin cache drift (or unavailable) |
RAMP |
nodes due / level / XP (or RAMP: no graph) |
Notes:
SESSION_LOGemits only the last entry plus any same-session match — not the full file.REPEAT_PINis computed for you; trust it instead of re-scanning.MEMORYemits aTAILfor dedup awareness; fullCONTENTappears only whenMIGRATION_NEEDED: yes.- If the script prints
ERROR: No project detected, say so and stop — pin is project-scoped.
Preferences (compute once, before Step 0)
Read the CONFIG section's YES_ALL value and combine with $ARGUMENTS:
- yes_all = (
--yes-allor--yaspresent in$ARGUMENTS) OR (CONFIG.YES_ALLisyes). If--askis present in$ARGUMENTS, force yes_all = false (one-off override of a saved preference). - save =
--saveor--yaspresent in$ARGUMENTS.
(--yas is shorthand for --yes-all --save — run non-interactively now and
persist the preference for future sessions.)
When save is true, run this once now and surface its output line:
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.
- 5d ago First seen · 222 lines · 0 tokens per session scan A de1a366a6612
pin is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,688 tokens. 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
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
lessons-compact
Compact MEMORY/LESSON.md by deduplicating near-identical lessons, merging same-root-cause lessons, and pruning stale ones — without losing any unique signal. Delegates the analysis to the lessons-compactor agent.
lessons
View project lessons in MEMORY/LESSON.md (project root) and append a compact "never reproduce" lesson.
scope
Search your Claude Code session history (full-text, always fresh).
unwrap
You are resuming a Claude Code session. Execute all steps below in order — no confirmation needed.
instincts
Inspect, promote, or clear learned instincts for this project. Captures patterns across sessions — opt-in, synchronous, no background capture.