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/marcusquinn/aidevops/pulse-checkgit clone --depth 1 https://github.com/marcusquinn/aidevopsWrote 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/marcusquinn/aidevops/pulse-check)<a href="https://agentmods.dev/commands/marcusquinn/aidevops/pulse-check"><img src="https://agentmods.dev/badge/commands/marcusquinn/aidevops/pulse-check.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 | $0.00014 | $0.00436 |
| Opus 5 | $0.00007 | $0.00218 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
pulse-check 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.
What it actually says
Run a bounded pulse/worker productivity check for interactive sessions.
Arguments: $ARGUMENTS
Goal
Answer “is the pulse using available concurrency and model/provider allowance?” from canonical current-state evidence, not process snapshots or log mtimes.
Procedure
-
Run the deterministic helper first:
~/.aidevops/agents/scripts/pulse-check-helper.sh report $ARGUMENTS -
If the user asks for machine-readable evidence:
~/.aidevops/agents/scripts/pulse-check-helper.sh json $ARGUMENTS -
If the report identifies a specific issue whose worker stopped progressing, inspect its bounded blocker lifecycle before opening raw logs:
~/.aidevops/agents/scripts/pulse-diagnose-helper.sh issue <N> --repo <owner/repo> -
If the user explicitly asks to file self-improvement work, or this is the scheduled daily routine, use deduplicated apply mode:
~/.aidevops/agents/scripts/pulse-check-helper.sh apply $ARGUMENTS
Interpretation
- Prioritise 5–15 minute current-state evidence for “is work happening now?” claims.
- Use 24h/48h aggregates only for trend context and failure-family clustering.
- An issue is worth filing only when the helper marks a finding
autofile=trueor you can cite equivalent evidence from the helper JSON. - Do not publish private repo names, local paths, issue titles, or raw worker examples in public comments/issues; the helper output is aggregate by design.
Verification references
.agents/reference/diagnostics-discipline.md.agents/reference/worker-diagnostics.md.agents/scripts/tests/test-pulse-check-helper.sh
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 · 62 lines · 14 tokens per session scan A e8ff91ef9af8
pulse-check is a command published in the GitHub repository marcusquinn/aidevops (391 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 436 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
audit
Execute the canonical workflow: .agent/workflows/audit.md.
gsd:new-milestone
Start a new milestone cycle — update PROJECT.md and route to requirements.
gsd:execute-phase
Execute all plans in a phase with wave-based parallelization.
gsd:audit-milestone
Audit milestone completion against original intent before archiving.
gsd:progress
Check project progress, show context, and route to next action (execute or plan).
gsd:insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.