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-resumegit 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 | $0.00776 |
| Opus 5 | $0.00000 | $0.00388 |
| Sonnet 5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
pp-resume 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Project Session
Start a new chat session with full project context loaded.
Arguments
$ARGUMENTS
Purpose
This is the FIRST command to run when starting a new chat session. It:
- Loads all project context into memory
- Understands current state
- Prepares to continue work
- Optionally focuses on specific direction from query
Execution Instructions
Step 1: Verify Project Exists
ls .context/project/INDEX.md
If not found, inform user: "No project structure found. Run /pp-init first."
Step 2: Read Root Context
Read these files in order:
.context/project/INDEX.md- Project overview, subprojects, active subproject, high-level status.context/project/WORKFLOW.md- How this system works.context/project/PRINCIPLES.md- Methodology and rules.context/project/LESSONS.md- Past learnings
Step 3: Read Active Subproject Context
From INDEX.md, identify active subproject, then read:
.context/project/{active}/STATUS.md.context/project/{active}/TODO.md.context/project/{active}/CODEBASE.md.context/project/{active}/LESSONS.md.context/project/{active}/PRINCIPLES.md(if exists - overrides root)
Step 4: Read Recent Changes
Read last 3-5 entries from:
.context/project/{active}/CHANGELOG.md
Step 5: Process Optional Query
If query provided:
- Parse for direction (e.g., "continue booking flow", "fix the API bug")
- Focus context on relevant TODO items
- Identify relevant LESSONS if debugging
Step 6: Check for Next Session Instructions (NEW)
After loading all standard files, check for continuation instructions:
ls .context/project/{active}/NEXT.md
If NEXT.md exists:
- Read
.context/project/{active}/NEXT.md - Extract history file path from NEXT.md
- Read that history file for previous session context
- Note the full chat transcript path (but DO NOT load it)
If NEXT.md does NOT exist:
- Skip this step, proceed to summary
Step 7: Generate Resume Summary
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 · 124 lines · 0 tokens per session scan A bdc5c5fdaf15
pp-resume 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 776 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.