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.
git clone --depth 1 https://github.com/bybren-llc/a-safe-pulseWrote 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/bybren-llc/a-safe-pulse/checkpoint)<a href="https://agentmods.dev/commands/bybren-llc/a-safe-pulse/checkpoint"><img src="https://agentmods.dev/badge/commands/bybren-llc/a-safe-pulse/checkpoint.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 5.1 | $0.00008 | $0.00650 |
| Opus 5 | $0.00004 | $0.00325 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
checkpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are saving a session checkpoint for cross-session continuity.
Security rule: Do NOT store secrets, raw tokens, credentials, or sensitive customer data in checkpoint files.
1. Determine Ticket
Extract the ticket number:
# Auto-detect from branch name
TICKET=$(git branch --show-current 2>/dev/null | grep -oE 'ASP-[0-9]+')
echo "Detected ticket: $TICKET"
If $ARGUMENTS was provided, use that instead. If no ticket can be determined, inform the user and stop — checkpoints require a ticket context.
2. Gather Git State
# Last commit
git log -1 --oneline
# Unpushed commits
git log origin/dev..HEAD --oneline 2>/dev/null | wc -l
# Uncommitted changes
git status --porcelain | wc -l
3. Summarize Session
Based on conversation context, create a summary covering:
- Completed: What was accomplished this session
- Next Steps: What should happen next (ordered by priority)
- Decisions Made: Key decisions with rationale
- Blockers: Any blocking issues (or "None")
- Open Questions / Risks: Unresolved uncertainty that would get lost across sessions
- Status: In Progress / Blocked / Ready for Review
4. Write Checkpoint (Canonical)
Write the checkpoint to .claude/state/checkpoints/ASP-{number}.md:
## Session Checkpoint — {today's date}
**Ticket**: ASP-{number}
**Branch**: {branch name}
**Status**: {status}
### Completed
- {bullets from summary}
### Next Steps
- {bullets from summary}
### Decisions Made
- {bullets with rationale}
### Blockers
- {if any, or "None"}
### Open Questions / Risks
- {unresolved items}
### Git State
- Last commit: {hash} {message}
- Unpushed: {count} commits
- Uncommitted: {yes/no}
5. Update Pointer
Write the ticket ID to .claude/state/checkpoints/current.md:
ASP-{number}
This overwrites any previous pointer. Only one ticket is "current" at a time.
6. Optional: Mirror to Memory
If the Claude Code memory system is available, optionally mirror the checkpoint to:
~/.claude/projects/.../memory/checkpoint.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 · 101 lines · 0 tokens per session scan A c65a49fc955c
checkpoint is a command published in the GitHub repository bybren-llc/a-safe-pulse (9 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 650 once invoked, about $0.0000 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 2026-09-04.
Other commands, from other repositories
vouch-propose-from-pr
Distill a merged PR into vouch claim proposals.
close
Close org-os session — summarize, write memory, commit, push.
wrap
End-of-session ritual. Updates handoff, priorities, daily log, and triggers synapse hygiene. Optional git commit with --commit flag.
checkpoint
Full memory flush — refresh state.md, append to activity log, route any new decisions/insights, then commit and push.
conclude
Use at session end to save project learnings and produce a commit message.
capture
Run stackmemory capture to commit current work and generate a handoff prompt for the next session.