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 skills/spumer/i-m-senior-developer/planner-reflectnpx skills add spumer/i-m-senior-developer --skill planner-reflectgit clone --depth 1 https://github.com/spumer/i-m-senior-developerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/spumer/i-m-senior-developer/planner-reflect)<a href="https://agentmods.dev/skills/spumer/i-m-senior-developer/planner-reflect"><img src="https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/planner-reflect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01007 |
| Opus 5 | $0.00020 | $0.00504 |
| Sonnet 5 | $0.00008 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
planner-reflect 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 4d ago.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner-Reflect — post-task learning
Compare the saved execution plan with what actually happened. Append only supported, reusable lessons to <project-root>/.claude/planner-context.md, then return a short Lessons learned summary.
Reflection observes completed work. It does not revise the plan, change code, invoke agents, or start another command.
Evidence sources
Read these sources in order:
<feature-dir>/PLANNER_EXECUTION.md— planned phases, agents, models, estimates, risks, and gates. This is the required source.git logand the changed-file list since the plan — completed work and scope changes.- Files under
<feature-dir>/review-request-changes/— confirmed defects and repeated categories. - Agent results available in the current session — retries, escalation, and blocked work.
- User messages from the current session — explicit corrections to the process or result.
ARCHITECTURE.md may be read to distinguish an implementation deviation from an architecture change, but it is supporting evidence, not a sixth independent source.
A legacy PLANNER_OUTPUT.md is historical context only. Do not use it as the current execution plan.
Missing evidence
- No
PLANNER_EXECUTION.md→ returnnothing to reflect on; run /plan on the architecture firstand write nothing. - No commits or changed files since the plan → return
plan exists but was not executed; nothing to reflect onand write nothing. - No current-session agent results → continue with Git, review files, and user messages; state that agent-run evidence was unavailable.
- Any other partial evidence → continue and list the unavailable sources in the summary.
Do not reconstruct a missing plan from Git history.
Lesson types
Write a lesson only when its trigger is visible in the evidence.
Agent gap
Trigger: the orchestrator used a generic fallback because .claude/planner-context.md had no active agent for the required role or stack.
Destination: agent catalog. Record the missing role, observed fallback, and date. Do not blame the agent or orchestrator.
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.
- 4d ago First seen · 112 lines · 41 tokens per session scan A 1daebb191200
planner-reflect is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,007 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 skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
grid-ctf-ops
Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.