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/unclecode/claude-code-tools/pp-checkpointgit clone --depth 1 https://github.com/unclecode/claude-code-toolsWhat 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 | $0.01666 |
| Opus 5 | $0.00000 | $0.00833 |
| Sonnet 5 | $0.00000 | $0.00333 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
pp-checkpoint 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 yesterday.
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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session Checkpoint
Save current chat session state and prepare instructions for next session.
Arguments
$ARGUMENTS
Optional query to add extra guidance for the next session. This query will be incorporated into the "What To Do Next" section of NEXT.md.
Examples:
/pp-checkpoint focus on fixing the auth bug first/pp-checkpoint user will provide new API docs tomorrow/pp-checkpoint skip T260, move directly to T262
Purpose
Called at the end of a chat session (or before hitting token limits) to:
- Create compact summary of current session (history file)
- Save comprehensive "what to do next" instructions (NEXT.md)
- Optionally create AI-compressed dump of chat history
- Link to full chat transcript
Execution Instructions
Step 1: Identify Current Session
# Get current working directory
pwd
# Convert to Claude projects path
# Example: /Users/unclecode/devs/project
# Becomes: ~/.claude/projects/-Users-unclecode-devs-project/
# Find most recent .jsonl file (exclude agent-* files)
ls -lt ~/.claude/projects/-Users-unclecode-devs-{converted-path}/*.jsonl | grep -v "agent-" | head -1
# Extract UUID from filename
# Example: 530170ff-52f5-4ad6-a333-22a09bd64773.jsonl
# UUID: 530170ff-52f5-4ad6-a333-22a09bd64773
Step 2: Determine Active Subproject
Read .context/project/INDEX.md to identify active subproject.
Step 3: Ask User About Chat History Dump
ALWAYS ask the user:
Before saving checkpoint, do you want me to create a compressed dump of this chat session?
This will use AI to compress the full conversation into a readable summary (~5-10% of original size) that captures all important details, decisions, and code changes.
Options:
1. **Yes** - Create compressed dump (takes ~30-60 seconds)
2. **No** - Skip dump, just save checkpoint files
Note: The raw .jsonl transcript is always available for grep/search regardless.
If user says Yes:
- Run the
/compress-chatcommand on the current session - Save compressed output to
.context/project/{active}/history/{uuid}-{YYYY-MM-DD}-dump.md
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.
- yesterday First seen · 248 lines · 0 tokens per session scan A c5921a0c7045
pp-checkpoint is a command published in the GitHub repository unclecode/claude-code-tools (4 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,666 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
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.