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-pullgit 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 | $0.00023 | $0.00821 |
| Opus 5 | $0.00012 | $0.00411 |
| Sonnet 5 | $0.00005 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
planner-pull 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read-only-by-default Planner sync. Do the following:
Step 1: Get your Planner user ID
Run az rest --method GET --url "https://graph.microsoft.com/v1.0/me?\$select=id,displayName,mail" and capture .id. Cache it in a bash variable for this session.
Step 2: Pull tasks from all 3 active plans in parallel
Plan IDs (authoritative list — source of truth is ~/CLAUDE.md "Microsoft Planner Reference"):
- IT Operations:
<YOUR_PLAN_ID_1> - Enterprise Engineering & Operations:
<YOUR_PLAN_ID_2> - AI Initiatives:
<YOUR_PLAN_ID_3>
For each plan, run:
az rest --method GET --url "https://graph.microsoft.com/v1.0/planner/plans/<planId>/tasks"
Step 3: Filter to tasks assigned to you
From each plan's value array, keep tasks where assignments contains your user ID as a key. Grab per-task: id, title, percentComplete, dueDateTime, bucketId, @odata.etag.
Step 4: Parse ~/CLAUDE.md for existing anchors
Read ~/CLAUDE.md. For every strategy bullet that already has an HTML anchor of the shape <!-- planner:<taskId> -->, build a map { taskId → { line_number, current_pct_from_bullet, title_from_bullet } }.
Step 5: Build the delta report
Group tasks by plan. For each task, classify as:
- ✅ synced — has anchor in CLAUDE.md AND
%Completematches (tolerance: exact integer match) - 🟡 drift — has anchor but
%Completediffers (Planner authoritative) - 🔴 unlinked — not in CLAUDE.md yet (no anchor), probably needs adding to a strategy
- ⚫ orphan — anchor in CLAUDE.md but task no longer exists in Planner (closed/deleted)
Display the report as a clean table, one section per plan, with these columns: | Status | Title | Planner % | CLAUDE.md % | Due | Bucket |
Step 6: Propose updates
After the table, list the proposed changes to ~/CLAUDE.md:
- For each 🟡 drift: show before/after of the bullet line
- For each 🔴 unlinked: suggest which OBJ/Strategy section it would fit under based on title similarity (don't auto-insert; just propose)
- For each ⚫ orphan: suggest removing the anchor and marking the bullet with
<!-- planner:closed -->
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 · 54 lines · 23 tokens per session scan A 975364afa164
planner-pull is a command published in the GitHub repository codebloodedai/claude-code-ops-commands (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 821 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 2026-08-31.
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.