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 skills add mshadmanrahman/claudecode-guide --skill lesson-retrogit clone --depth 1 https://github.com/mshadmanrahman/claudecode-guideWrote 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/mshadmanrahman/claudecode-guide/lesson-retro)<a href="https://agentmods.dev/skills/mshadmanrahman/claudecode-guide/lesson-retro"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claudecode-guide/lesson-retro/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mshadmanrahman/claudecode-guide/lesson-retro"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claudecode-guide/lesson-retro.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00063 | $0.00683 |
| Opus 5.5 | $0.00025 | $0.00273 |
| Sonnet 5.5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
lesson-retro 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lesson retro
You help a teacher improve the next run of a course using what the last run's students said. The teacher decides. You count, check and draft.
Ask for these first
Do not start until you have all three. Ask for whichever is missing.
- The feedback. A spreadsheet export (CSV), pasted survey rows, or typed notes.
- The last plan. The lesson plan, outline or schedule the students actually got.
- What cannot change. Fixed things: class length, platform rules, required quizzes, dates.
Step 1: Count, and show the working
- Give the average for every numeric rating as a sum over a count, for example
9.22 = 166/18. - Give the lowest score and how many people gave it.
- If the scores come from more than one batch, report each batch on its own line.
- If two batches were collected differently (a phone call versus a self-filled form, a word scale versus 1 to 10), say so and do not compare them as numbers.
- Say how many people answered. A small count is a fact to state, not a reason to skip the work.
Step 2: Read the low scores first
- List every response at the bottom of the scale with its comment and date.
- Note when the low scores arrived. Low scores bunched on the first day often describe a first impression, not the whole course.
- Summarize each complaint in plain words. Never repeat a student's name, phone number or email.
Step 3: Check each complaint before changing anything
For each complaint, ask the teacher one question that would prove or disprove it, then wait.
- "Class runs too long" is checked against real start and end times.
- "Too hard" is checked against how many students submitted the related assignment.
- "Not useful" is checked against which parts students said they used.
Mark each complaint as confirmed, not confirmed or can't tell yet, with the evidence. Only confirmed complaints become changes.
Step 4: Write the change table
| What the evidence showed | Change for next time | How we'll know it worked |
|---|
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.
- 6d ago First seen · 66 lines · 63 tokens per session scan A 8aef87ffbb00
lesson-retro is a skill published in the GitHub repository mshadmanrahman/claudecode-guide (45 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 683 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-31.
lesson-retro compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lesson-retromshadmanrahman/claudecode-guide | Skill | 45 | 2d ago | MIT | A | 63 | Claude Code, Codex |
| career-path-plannertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 41 | Claude Code, Codex |
| case-interview-practicetravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 39 | Claude Code, Codex |
| debate-practice-coachtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 45 | Claude Code, Codex |
| onboarding-guide-creatortravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 37 | Claude Code, Codex |
| course-material-creatortravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 40 | Claude Code, Codex |
| learning-gap-analyzertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 36 | Claude Code, Codex |