bennu: Skill for Claude Code

.claude/skills/retro/SKILL.md

retro is a skill for Claude Code from Lengros/bennu. It costs 54 tokens per session (3,040 once invoked), scanned A, original, MIT.

A recurring project review based on activity logs, blocked-work records, and earlier lessons. A retrospective, or retro, is a structured look back at what went well and what caused friction.

In plain words
What is it for?
Use it when a retro trigger exists or the monthly review is due, to identify recurring problems, assess project health, and propose improvements.
Why use it?
It turns recorded work history into a health report instead of relying on memory or incomplete log searches.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Lengros/bennu's own configuration. It tells Claude Code how to work on bennu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bennu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Lengros/bennu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Lengros/bennu/main/.claude/skills/retro/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Lengros/bennu

Made for: Claude Code.

Wrote 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.

agentmods badge for retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/lengros/bennu/retro.svg)](https://agentmods.dev/skills/lengros/bennu/retro)
Your own site
<a href="https://agentmods.dev/skills/lengros/bennu/retro"><img src="https://agentmods.dev/badge/skills/lengros/bennu/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.03040
Opus 5 $0.00027 $0.01520
Sonnet 5 $0.00011 $0.00608
Haiku 4.5 $0.00005 $0.00304

Measured 6d ago against content hash cc8683033fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

.claude/skills/retro/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/retro — LEARN-loop consumer

When to run

  • telemetry/retro.flag exists in this project (session-start.sh injects its content; CLAUDE.md startup reads it as fallback).
  • Monthly cadence: session-end.sh also sets retro.flag when the last type:"retro" marker is >30 days old (or, with no retro ever, the oldest activity is >30d), so the loop turns even in a low-friction month. No external cron — the calendar check rides the existing flag mechanism.

Arguments: none.


Parsing discipline — read before any step

Parse every telemetry line with a real JSON parser (python3 -c 'json.loads(...)' or jq), then match on the parsed type field. Never select records by string-matching "type":"run" with grep, and never field-split on a "key":" literal (e.g. awk -F'"ts":"'). The corpus is NOT uniformly formatted: log-run.sh historically emitted spaced JSON ({"ts": "...", "type": "run", ...}) while the hooks emit compact JSON ({"ts":"...","type":"..."}). A string-matcher keyed on the compact shape silently drops every run record — which produces a false "0 runs / R2,R3,reuse unmeasurable" report even when dozens of runs exist (this exact failure occurred 2026-06-13). json.loads is whitespace-agnostic and reads both shapes; that is the only safe reader. The two "type":"..." and ts >= window_start comparisons named in the steps below are logical predicates over parsed objects, not grep patterns.


Step 1 — Determine the review window

Read telemetry/runs.jsonl and parse each line as JSON (see Parsing discipline above). Scan all parsed records for type == "retro" events. The session-end record shape is defined in [Observed: .claude/hooks/session-end.sh:93-95]. Take the most recent one's ts field as window_start. If none found, set window_start = now − 30 days. Also record prior_retro_ts = the second-most-recent type:"retro" ts if one exists (consumed by the skip-rate watch in section d); if there are fewer than two retro markers, prior_retro_ts is undefined.

Read the full file on GitHub · 226 lines

Changes

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.

  1. 6d ago First seen · 226 lines · 54 tokens per session scan A cc8683033fa3

Subscribe to this mod's changes

retro is a skill published in the GitHub repository Lengros/bennu (2 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 3,040 once invoked, about $0.0003 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 2026-08-31.