Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. 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/friedbotstudio/baseline/main/.claude/skills/retrospective/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/retrospective)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/retrospective"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/retrospective/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/friedbotstudio/baseline/retrospective"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.01078 |
| Opus 5.5 | $0.00000 | $0.00431 |
| Sonnet 5.5 | $0.00000 | $0.00216 |
| Haiku 4.5 | $0.00000 | $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 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.
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.
- 1mo ago First seen · 69 lines · 0 tokens per session scan A 53c833ba1446
retrospective is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,078 tokens. 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
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.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.