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/planner-pushgit 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 | $0.00025 | $0.01036 |
| Opus 5 | $0.00013 | $0.00518 |
| Sonnet 5 | $0.00005 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
planner-push 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 -X PATCH "https://<YOUR_DASHBOARD_FUNC_APP>/api/projects/<taskId>" \ How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write-back sync. Invoked when I (Claude) have just finished some work — a commit, a deploy, a bug fix, a vault update — and need to reflect it in Planner + Pulse immediately.
Arguments (conversational — the user may supply these directly or I should infer them from current session context)
- taskId (required): the Planner task ID. If the user invokes /planner-push without args, ask which task — or propose the most likely one based on what we just worked on. If there's an anchor in
~/CLAUDE.mdfor a bullet we just touched, use that taskId. - newPercent (required): integer 0–100. If not provided, propose one based on the work done ("we just shipped X, I'd mark it Y%").
- statusNote (optional): a ≤200-char natural-language summary of what was done. Defaults to a one-liner inferred from the current session.
Step 1: Confirm intent
Before any writes, show the user:
About to update:
Task: <title> (<taskId>)
Plan: <plan name>
%: <old> → <new>
Note: <statusNote>
This will write to:
1. Planner (MS Graph)
2. Pulse history (execdash PATCH)
3. ~/CLAUDE.md bullet (the anchor that points to this task)
Proceed? [y/N]
Wait for explicit confirmation. NEVER write without a yes.
Step 2: Fetch current Planner task state + etag
az rest --method GET --url "https://graph.microsoft.com/v1.0/planner/tasks/<taskId>"
Capture [email protected]. Fail out with a clear message if the task doesn't exist or I can't read it.
Step 3: PATCH Planner percentComplete
az rest --method PATCH \
--url "https://graph.microsoft.com/v1.0/planner/tasks/<taskId>" \
--headers "Content-Type=application/json" "If-Match=<etag>" \
--body '{"percentComplete": <newPercent>}'
If the response is 204/200, continue. If 412 (etag mismatch), re-fetch and retry once. If still failing, stop and report.
Step 4: Append a history entry to Pulse
Call the Pulse Functions API to upsert the project's history:
curl -X PATCH "https://<YOUR_DASHBOARD_FUNC_APP>/api/projects/<taskId>" \
-H "Content-Type: application/json" \
-d '{"history":[{"date":"<ISO-8601>","action":"<statusNote>","by":"<YOUR_EMAIL>"}]}'
Caveat: Pulse's function may require SWA-auth headers or managed-identity — if the direct PATCH returns 401/403, tell the user and suggest routing through the authenticated SWA instead (curl https://<YOUR_DASHBOARD_DOMAIN>/api/projects/<taskId>). Don't fail silently.
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 · 80 lines · 25 tokens per session scan A 4697f2f54357
planner-push is a command published in the GitHub repository codebloodedai/claude-code-ops-commands (2 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,036 once invoked, about $0.0001 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.