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/end-work)<a href="https://agentmods.dev/commands/bybren-llc/a-safe-pulse/end-work"><img src="https://agentmods.dev/badge/commands/bybren-llc/a-safe-pulse/end-work.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 | $0.00006 | $0.00906 |
| Opus 5 | $0.00003 | $0.00453 |
| Sonnet 5 | $0.00001 | $0.00181 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
end-work 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are completing a work session. Execute final checklist before context switch or session end.
Completion Checklist
1. Work Status
Verify current state:
git status
git log origin/dev..HEAD --oneline
Status options:
- Work Complete: Ready for PR
- Work In Progress: Safe stopping point, commit and document
- Blocked: Document blockers
2. Commit All Work
If uncommitted changes:
git add .
git commit -m "type(scope): description [ASP-XXX]"
Verify all work committed:
git status # Should show clean working tree
3. Documentation Status
Quick check:
- Inline comments for complex logic?
- README updated if new feature?
- CLAUDE.md/CONTRIBUTING.md updated if workflow changed?
- Linear ticket status current?
4. Update Linear Ticket
Note: Tickets referenced in commit messages (e.g.,
[ASP-XXX]) auto-sync to Done when the PR merges via the GitHub-Linear integration. Manually close any child stories not referenced in commits.
Based on work status:
If Complete:
- Update ticket status to "Ready for Review" or "In Progress"
- Add comment summarizing work done
- Link to PR if created
If In Progress:
- Update ticket with progress notes
- Document any blockers or questions
- Set status appropriately
If Blocked:
- Document blocker clearly
- Add comments to ticket
- Tag appropriate people
Use Linear MCP:
mcp__linear-mcp__update_issue
mcp__linear-mcp__create_comment
5. Save Checkpoint (conditional)
Save a session checkpoint if meaningful work was done:
Required when ALL of these are true:
- Branch matches
ASP-\d+pattern (SAFe ticket branch) - There is meaningful progress, a blocker, or pending next steps
- Not in detached HEAD or non-SAFe branch
Skip checkpoint when:
- No ticket branch (e.g.,
dev,main, detached HEAD) - No meaningful work was done this session
- User explicitly declines
If checkpointing:
- Determine ticket from branch:
git branch --show-current | grep -oE 'ASP-[0-9]+' - Gather git state: last commit, unpushed count, uncommitted status
- Summarize: completed, next steps, decisions, blockers, open questions
- Write to
.claude/state/checkpoints/ASP-{number}.md - Update
.claude/state/checkpoints/current.mdpointer - If status is "Ready for Review" or "Done", clear
current.md(delete the file)
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 · 155 lines · 6 tokens per session scan A b098e9a729c6
end-work is a command published in the GitHub repository bybren-llc/a-safe-pulse (9 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 906 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
gsd:quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
backlog-git
Control de versiones para backlogs de proyectos.
company-repo
Gestionar el repositorio Company Savia: crear, conectar, estado, sincronizar. El repositorio compartido de la empresa para conocimiento, mensajería y estado.
gsd:pause-work
Create context handoff when pausing work mid-phase.
gsd:remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
weekly-summary
Generate weekly work summary from git activity.