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/codebloodedai/claude-code-ops-commands/pulse-updategit clone --depth 1 https://github.com/codebloodedai/claude-code-ops-commandsWhat 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 | $0.00030 | $0.02126 |
| Opus 5 | $0.00015 | $0.01063 |
| Sonnet 5 | $0.00006 | $0.00425 |
| Haiku 4.5 | $0.00003 | $0.00213 |
Grade A, and why
pulse-update scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://<YOUR_DASHBOARD_DOMAIN>/api/projects How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive editor for Pulse project briefs. Used AFTER finishing a chunk of work to reflect it in the exec dashboard. Distinct from /planner-push — this command is editorial (brief/narrative content), /planner-push is mechanical (% complete).
Pulse brief data shape
Pulse projects are keyed by their Planner task ID and stored in Azure Table Storage. Each project has these dashboard-only editable fields (set via PATCH /api/projects/{taskId}):
| Field | Type | Semantics |
|---|---|---|
brief.objective |
string | What the project is trying to achieve. Rarely changes. |
brief.currentReality |
string | Where we are today. Should reflect the most recent material change. |
brief.risks |
string[] | Active risks/blockers. Add new ones, remove resolved ones. |
nextActions |
{ action, owner, dueDate }[] |
Forward-looking work items. Replaces fully on write. |
history |
{ date, action, by }[] |
Append-only feed of what has been done. |
priority |
int | Dashboard ordering hint. Don't touch unless explicitly asked. |
The Planner-managed fields (title, percentComplete, dueDate, assignees) flow FROM Planner and should NOT be touched here — use /planner-push for those.
Step 1: Identify which project we're updating
If the user invokes /pulse-update without args, determine the target:
- If the last ~20 turns of conversation are clearly about one project (e.g., we just fixed project audio, we just committed a backend feature), propose that project and its Planner task ID.
- If there's no clear context, list the open projects from
/api/projectsand ask which one. - If the user passes a name ("pulse-update project-alpha") or a Planner task ID, use that directly.
- Prefer resolving via
<!-- planner:<taskId> -->anchors in~/CLAUDE.md— they're the deterministic join key.
Step 2: Fetch the current brief
Hit Pulse's GET endpoint to retrieve the current state of the project. Two paths:
Preferred: via authenticated SWA (works when a browser session is available)
curl https://<YOUR_DASHBOARD_DOMAIN>/api/projects
Requires an MSAL session. If we have Playwright already open on a <YOUR_DASHBOARD_DOMAIN> tab, reuse it via browser_evaluate to fetch the JSON.
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 · 182 lines · 30 tokens per session scan A 5f7ec1226684
pulse-update is a command published in the GitHub repository codebloodedai/claude-code-ops-commands (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 2,126 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.