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 xbklairith/kisune --skill retrogit clone --depth 1 https://github.com/xbklairith/kisuneWrote 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/xbklairith/kisune/retro)<a href="https://agentmods.dev/skills/xbklairith/kisune/retro"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/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/xbklairith/kisune/retro"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/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 | $0.00095 | $0.01338 |
| Opus 5.5 | $0.00038 | $0.00535 |
| Sonnet 5.5 | $0.00019 | $0.00268 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro
Overview
A retro improves the environment the next agent works in, not the code from the last session. The evidence is the session log; the output is a short, severity-ordered list of environment changes, each concrete enough to apply in one step.
Core principle: a check beats a rule. A mistake a machine can detect gets a check (lint rule, type check, test, hook, CI job). Prose in CLAUDE.md is the last resort, because every line there is loaded into every session and is obeyed only probabilistically.
1. Read the primary source
Read the actual log, not a recollection of it. Claude Code keeps logs per project; read this project's only:
python3 <this skill>/scripts/session_log.py list # sessions for cwd's project
python3 <this skill>/scripts/session_log.py show latest # or a SESSION_ID from list
python3 <this skill>/scripts/session_log.py show <id> --full # include the agent's prose
- Never glob across
~/.claude/projects/. Other directories there are private chats from unrelated projects. The script derives the one directory from the project path; use it rather thanfind/grepover the parent. - If the user hands you a written log or notes instead, use that.
- Redact. Logs contain pasted keys and tokens. Never quote a secret value in the retro; name where it was exposed.
The show summary flags the usual waste: files read repeatedly, commands re-run, failed tool calls, and how far into the session the first edit came.
2. Find candidates
For each friction point in the log, ask which category removes it next time:
| Category | Signal in the log | Change |
|---|---|---|
| Automated checks | The agent made a mistake a tool could catch; or the repo has no guardrail at all (no hook, no CI running lint/type/test) | Wire the check. First read the repo's existing lint/check/CI config: a check that exists but is unwired or broken is the finding, not a new one |
| Review rules | The mistake is a judgement call and review missed it | Add it to what the reviewer reads (the repo's CODING_STANDARDS.md or the review checklist the team runs) |
| Navigation | Long searches for a file or fact; hidden coupling between files | A one-line pointer in the place the agent looked first |
| Steering trims | CLAUDE.md lines that change no behavior ("write clean code"), or rules a check now enforces |
Delete them |
| Tool economy | Expensive or repeated tool calls; a noisy CLI or MCP | A script, a flag, a narrower command |
| Information access | A fact the agent needed but could not see (server logs, a dashboard, a schema) | Give read access: tee logs to a file, a read-only token, a schema dump |
| Skills | The same multi-step procedure re-derived each session | A skill (write it with skill-maker) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 75 lines · 95 tokens per session scan A 3a7a5257a067
retro is a skill published in the GitHub repository xbklairith/kisune (3 stars, last pushed 8d ago), licensed MIT. It adds 95 tokens to every session and 1,338 once invoked, about $0.0004 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 2026-10-07.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.