planner-link

A one-time command that links Microsoft Planner tasks to strategy bullets in a CLAUDE.md file using stable task identifiers.

In plain words
What is it for?
Use it to fetch tasks, match them to existing bullets, identify unassigned tasks, and add Planner anchors where appropriate.
Why use it?
It gives later synchronization commands a reliable way to match Planner tasks with the correct local bullets.

Command

Install

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.

agentmods
npx agentmods add commands/codebloodedai/claude-code-ops-commands/planner-link
Clone the repo
git clone --depth 1 https://github.com/codebloodedai/claude-code-ops-commands
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash f09bc8395232, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/planner-link.md · 85 lines

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...

Read the full file on GitHub · 85 lines

Changes

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.

  1. yesterday First seen · 85 lines · 22 tokens per session scan A f09bc8395232

Subscribe to this mod's changes

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.