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/mirinodev/maestro/historygit clone --depth 1 https://github.com/mirinodev/maestroWrote 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/mirinodev/maestro/history)<a href="https://agentmods.dev/commands/mirinodev/maestro/history"><img src="https://agentmods.dev/badge/commands/mirinodev/maestro/history.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 | $0.02438 |
| Opus 5 | $0.00000 | $0.01219 |
| Sonnet 5 | $0.00000 | $0.00488 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade C, and why
history scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$BACKUP_DIR" How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔸 history
Command to manage Claude Code conversation history. You can save, search, and export development history for each orchestra member (Git worktree).
Overview
mst history [options]
mst h [options] # alias
Usage Examples
Basic Usage
# List all histories
mst history --list
# Show history for specific branch
mst history --show feature-auth
# Export histories
mst history --export all-histories.json
mst history --export all-histories.md
# Merge all histories into one file
mst history --merge merged-history.md
History Management
# Cleanup unnecessary histories
mst history --cleanup
# Sync history paths
mst history --sync
# Search histories
mst history --search "authentication"
# Output in JSON format
mst history --list --json
Options
| Option | Short | Description | Default |
|---|---|---|---|
--list |
-l |
Display history list | false |
--show <branch> |
-s |
Show history for specific branch | none |
--export <file> |
-e |
Export histories | none |
--merge <file> |
-m |
Merge all histories into one file | none |
--cleanup |
-c |
Cleanup unnecessary histories | false |
--sync |
Sync history paths | false |
|
--search <query> |
Search histories | none | |
--json |
-j |
Output in JSON format | false |
--days <n> |
-d |
Only histories within specified days | none |
History Storage Format
Claude Code histories are saved in the following format:
Directory Structure
~/.claude/history/
├── feature-auth.md
├── bugfix-login.md
├── experiment-ml.md
└── main.md
History File Content
# Claude Code History - feature/auth
## Session: 2025-01-20 10:30:00
### Human
Please implement authentication functionality. Use JWT.
### Assistant
I'll implement authentication functionality with JWT. First, let's install the necessary packages...
---
## Session: 2025-01-20 14:00:00
### Human
Please add tests.
### Assistant
I'll add tests for the authentication functionality...
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.
- 4d ago First seen · 459 lines · 0 tokens per session scan C 3ca83d88794a
history is a command published in the GitHub repository mirinodev/maestro (9 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,438 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
retro
Post-work command that extracts learnings and updates the learning registry.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.
freshen
Re-check the vault's live-state claims against the world. Walks now memory files for verify lines, runs each read-only command, reports CONFIRMED / STALE / CHECK-FAILED / UNVERIFIABLE. Report-first — never edits memory.
lint
The lint ritual — an entropy-reduction pass over the memory vault. Mechanical checks by script, judgment checks by you; report-first, never deletes. Monthly cadence, or after a ship-week.
learn-eval
Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).