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 skills/brain-bootstrap/claude-code-brain-bootstrap/checkpointnpx skills add brain-bootstrap/claude-code-brain-bootstrap --skill checkpointgit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWhat 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 | $0.00039 | $0.00377 |
| Opus 5 | $0.00019 | $0.00188 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
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 2d 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.
What it actually says
Checkpoint Skill
Save session state for clean handoff to the next session.
When to use
- Context window is getting full (preemptively)
- Before ending a session with work in progress
- Before a long-running operation that might reset context
Protocol
1. Record current state in claude/tasks/todo.md
# Task: <current task title>
_Checkpointed: {{DATE}}_
**Goal:** <what done looks like>
**Branch:** <output of: git branch --show-current>
**Loaded docs:** claude/architecture.md, claude/rules.md, [others read this session]
## Completed Steps
- [x] 1. <step>
- [x] 2. <step>
## Remaining Steps
- [ ] 3. <next action — be specific>
- [ ] 4. <step>
## Next Action
> <Single most important thing to do when resuming>
## Uncommitted Files
<output of: git status --short | head -20>
## Notes
<Any constraints, blockers, or decisions made this session>
2. Update claude/tasks/lessons.md
If any corrections or new patterns were discovered this session, add them NOW.
3. Confirm to user
"Session state saved to claude/tasks/todo.md. To resume: use /resume."
Rules
- NEVER checkpoint without writing the Next Action explicitly
- NEVER skip lessons.md update if corrections were made
- Checkpoint early — better to checkpoint too often than to lose context
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.
- 2d ago First seen · 55 lines · 39 tokens per session scan A 91ac030b740f
checkpoint is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 377 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
implement
TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…
review-spec
Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.
chain-of-verification
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.
review-code
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
review-design
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.
design
Use in pre-implementation (idea-to-design) stages to understand spec/requirements and create a correct implementation plan before writing actual code. Turns ideas into a fully-formed PRD/design/specification and implementation-plan. Creates design docs and task lists in docs/wip/.