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-linkgit 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 | $0.00022 | $0.01026 |
| Opus 5 | $0.00011 | $0.00513 |
| Sonnet 5 | $0.00004 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
planner-link 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run this ONCE (or when adding new tasks) to bootstrap the Planner ↔ CLAUDE.md join keys. After this runs, /planner-pull and /planner-push can find every bullet deterministically.
Step 1: Get your Planner user ID
az rest --method GET --url "https://graph.microsoft.com/v1.0/me?\$select=id,displayName"
Step 2: Pull tasks from all 3 active plans
Same as /planner-pull step 2. For each task, extract: id, title, percentComplete, planId.
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>
Filter to tasks assigned to you OR with no assignee (orphans should be flagged).
Step 3: Read ~/CLAUDE.md and extract existing bullets
Read ~/CLAUDE.md. For every line matching:
- [ ] <text> `(<owner>)` `<pct>%` [optional trailing — comment]
- [x] <text> `(<owner>)` ...
capture: line number, checkbox state, full text, owner, pct, whether it already has a <!-- planner:... --> anchor.
Step 4: Match bullets to tasks
For each strategy bullet without an anchor, score every Planner task by text similarity against the bullet's text. Use a simple approach:
- Normalize both to lowercase, strip punctuation, drop stopwords (the, a, an, to, of, for, in, on, and)
- Compute token overlap / Jaccard similarity
- Prefer tasks in the same "domain" — bullets under OBJ-1 sections are more likely to match IT Operations plan tasks, OBJ-4 bullets match Enterprise Engineering
For each bullet, keep the top 3 candidate matches with their similarity scores.
Step 5: Show the proposed mapping
Display a table like:
BULLET → CANDIDATE MATCHES
(L45) Ship monitoring integration (you) 10% → 1. "Monitoring integration" (95%) [IT Ops] <EXAMPLE_TASK_ID>
→ 2. "SIEM Implementation" (42%) [IT Ops] bB-67cfwJE-VYOw...
→ 3. (no other candidates above 30%)
(L52) Harden password manager posture (you) 75% → 1. "improve password security posture" (88%) [IT Ops] <EXAMPLE_TASK_ID_2>
→ 2. "Integrate password manager with Azure SSO" (40%) [IT Ops] 2AusZtjQ-UaGdW...
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 · 85 lines · 22 tokens per session scan A f09bc8395232
planner-link is a command published in the GitHub repository codebloodedai/claude-code-ops-commands (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,026 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.