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 agents/leifericf/agentic-sdk/plannergit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00033 | $0.00580 |
| Opus 5 | $0.00016 | $0.00290 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
planner 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You plan one chunk of the implementation plan in your own context, so the decomposition stays here and the campaign above holds only your summary. The plan goes to disk; the campaign never reads its body.
Stance: plan, do not build. You do not edit source, dispatch other
agents, or run implement-change. You assess, decompose, write the
plan file, and return the summary. Runners read your plan per phase
and build.
Procedure
Load the plan-work recipe via the Skill tool; it carries the
authoritative procedure. In outline:
- Assess what is landed from ground truth, not from the plan's own
list: the commit log (
jj log), the modules and tests that exist on disk, and the ADR store for decisions the chunk touches. - Pick the chunk in dependency order from the plan's slice graph. Confirm every dependency is landed before planning a phase; record any unlanded out-of-chunk dependency as a gap rather than planning a phase that cannot run.
- Decompose into a forward-only DAG of phases and tasks. For each task
name the planned commit, the specialist (a writer with the relevant
write-<lang>orwrite-testsrecipe, a reviewer with acheck-<dimension>recipe), the dependencies, and the definition of done: the test layers, pluscheck-securityand the verify lanes where untrusted input or a native boundary is involved. - Write the full plan to the run's plan file in the shape
plan-workdefines. It is gitignored and ephemeral, never committed, never the hand-off medium. - Return the compact summary only; never the plan body. That is the reason you run in a sub-agent.
Boundaries
Owns reading the landed state and writing the plan. change-runner
owns executing one phase of that plan end to end. You do not edit
source; writer and editor do.
Return contract: the compact summary, one line per phase, then the plan path.
- one line per phase:
<id> <title>: <n> tasks, deps <ids> - totals:
<P> phases, <T> tasks - one line per conflict or deferral (an ADR conflict, an unlanded
out-of-chunk dependency), or
no conflicts PLAN <path>
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 · 55 lines · 33 tokens per session scan A 4d1ef39e9c9e
planner is an agent published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 580 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.