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/friedbotstudio/baseline/retrospectivenpx skills add friedbotstudio/baseline --skill retrospectivegit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00139 | $0.01078 |
| Opus 5 | $0.00069 | $0.00539 |
| Sonnet 5 | $0.00028 | $0.00216 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
retrospective 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retrospective — from recurring friction to structural enforcement
The baseline's enforcement funnel has three rungs: a landmine (a remembered failure pattern surfaced by advisory memory hooks), an advisory hook (a PreToolUse hook that surfaces the landmine inline before the risky call), and a hard gate (a blocking hook or consent gate). Friction that recurs should climb this funnel instead of being re-litigated every session. This skill is the climb's entry point.
This skill is a generator, not a workflow phase. It enters no Track Guard ordering and blocks nothing. It writes ONLY memory entries (via the canonical entry shape) and an inline report. It never edits hooks, never touches seed.md/CLAUDE.md, never creates enforcement — those are amendment-path changes the user drives.
Inputs
Gather in main context (Article II — no subagent judgment):
- The cycle window: since the last release tag, the epic's first commit, or a user-named range.
- The
landminesanddecisionscategories under.claude/memory/— what is already recorded. Read them shape-agnostically: a sharded store keeps one fact per file under<category>/, a flat one keeps## keyblocks in<category>.md. - Friction evidence inside the window: guard-trip messages in
.claude/state/logs/(hook log lines),docs/rca/*.mdpostmortems, integrate-failure yields in.claude/state/harness/*.log, and user corrections you can cite verbatim from the session or_resume.md.
Method
1. Collect candidate frictions
Sweep the inputs for events that happened more than once in the window, or once with high cost (a broken commit, a failed release, a consent near-miss). One-off annoyances are not retro material.
2. Classify each recurring friction
- Already a landmine? Re-verify the entry (Article IX.2); refresh
last-touchedand strengthen the entry body with the new occurrence. - New pattern? Draft a
landmines.mdentry in the canonical shape (stable key, occurrence citations,verified-at, verbatim quote when the source is a user correction). - Not memory-shaped (a spec gap, a missing test)? Route it to
backlog.mdas an entry instead — the retro records it; a future workflow fixes it.
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.
- 2d ago First seen · 69 lines · 0 tokens per session scan A 53c833ba1446
retrospective is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 139 tokens to every session and 1,078 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.