Borrowing it
Nothing to install: this file belongs to JeremyDev87/codingbuddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JeremyDev87/codingbuddy/master/.claude/skills/retro/SKILL.mdgit clone --depth 1 https://github.com/JeremyDev87/codingbuddyWrote 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/jeremydev87/codingbuddy/retro)<a href="https://agentmods.dev/skills/jeremydev87/codingbuddy/retro"><img src="https://agentmods.dev/badge/skills/jeremydev87/codingbuddy/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/jeremydev87/codingbuddy/retro"><img src="https://agentmods.dev/badge/skills/jeremydev87/codingbuddy/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 | $0.00036 | $0.01826 |
| Opus 5.5 | $0.00014 | $0.00730 |
| Sonnet 5.5 | $0.00007 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade B, and why
retro scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rl "[keyword]" ~/.claude/projects/*/memory/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Retrospective
Analyze what happened in the current session, extract learnings, and turn them into durable improvements — rules, feedback memories, or GitHub issues.
Follow every step in order. Stop and report if any step fails.
Core Principle
Learnings decay. If a retrospective doesn't happen immediately after the work, the insights are lost. Capture them while context is fresh, classify them by type, and route them to the right destination so they compound over time.
The Iron Law
NO RETRO WITHOUT EVIDENCE.
Every Keep, Problem, and Action must cite a specific event from the session — not a general feeling.
When to Use
- After completing parallel/batch work (taskmaestro waves, swarm, ultrawork)
- After a multi-step plan execution (PLAN → ACT → EVAL cycle)
- After a significant debugging session
- After any session where something surprising happened (good or bad)
- When the user explicitly asks to reflect on recent work
Don't use when:
- The session was trivial (single file edit, quick fix)
- No context.md or session history exists to analyze
Step 1: Gather Session Context
Read the session history from docs/codingbuddy/context.md:
cat docs/codingbuddy/context.md
If the file does not exist or is empty, check for alternative sources:
$ARGUMENTS— the user may pass a file path or description- Git log for recent commits on the current branch:
git log --oneline -20 - If no context is found, stop and tell the user: "No session history found. Run a PLAN → ACT cycle first, or pass a context file as argument."
Collect:
- Tasks attempted — what was planned
- Tasks completed — what actually shipped
- Tasks failed or blocked — what didn't work and why
- Timeline — rough sequence of events
Step 2: Keep Analysis
Identify what went well. For each item:
| Field | Description |
|---|---|
| What | The specific thing that worked |
| Evidence | Where in the session this happened (commit, step, decision) |
| Why it worked | Root cause of success — not luck, but a reproducible reason |
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.
- 1mo ago First seen · 243 lines · 36 tokens per session scan B d448c2a650df
retro is a skill published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,826 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…