benefriches: Skill for Claude Code

.claude/skills/reflect/SKILL.md

reflect is a skill for Claude Code from incubateur-ademe/benefriches. It costs 87 tokens per session (1,615 once invoked), scanned C, original, MIT.

A session review that looks for mistakes, corrections, unclear instructions, and failed attempts, then suggests lasting changes to project guidance files.

In plain words
What is it for?
Use it after a difficult or unsuccessful session to identify which project instructions should be clarified or changed.
Why use it?
It helps prevent the same problems from recurring by improving the instructions that guide future coding sessions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is incubateur-ademe/benefriches's own configuration. It tells Claude Code how to work on benefriches 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 benefriches configures →

Reuse

Borrowing it

Nothing to install: this file belongs to incubateur-ademe/benefriches. 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/incubateur-ademe/benefriches/main/.claude/skills/reflect/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/incubateur-ademe/benefriches

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 reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/reflect/github.svg)](https://agentmods.dev/skills/incubateur-ademe/benefriches/reflect)
Your own site
<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/reflect"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/reflect/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.

agentmods 80×15 button for reflect

Your own site · 80×15
<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/reflect"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00087 $0.01615
Opus 5 $0.00044 $0.00807
Sonnet 5 $0.00017 $0.00323
Haiku 4.5 $0.00009 $0.00161

Measured 12d ago against content hash daafe858fc58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

reflect scanned grade C with 2 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 12d 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.

description: Reflect on the current session to find mistakes, user corrections, ambiguous instructions, and failures — then propose durable root-cause fixes to the project's instruction docs (CLAUDE.md, .claude/rules, .c

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

description: Reflect on the current session to find mistakes, user corrections, ambiguous instructions, and failures — then propose durable root-cause fixes to the project's instruction docs (CLAUDE.md, .claude/rules, .c
.claude/skills/reflect/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect - Session Self-Improvement

Reflect on the current session and propose durable, root-cause fixes to the project's instruction surface (CLAUDE.md, .claude/rules/*, .claude/skills/*) so the mistakes, misunderstandings, or ambiguous instructions that occurred don't recur.

Bias toward the opposite of a point fix: when something went wrong, the interesting output is not "fix this file" but "which instruction doc was ambiguous / missing / mis-scoped such that a careful agent got it wrong — and how should that doc be reworded?"

This is deliberately different from revise-claude-md:

  • Signal philosophy: anchored on externally-observable failure signals (corrections, doc-misreads, failing commands, loops) — never open-ended "what could I have done better" introspection. Unaided self-critique of otherwise-correct work degrades quality; don't do it.
  • Target surface: the full instruction surface (CLAUDE.md + rules + skills), not just CLAUDE.md.
  • Fix type: biased toward editing the ambiguous line that misled you, not just appending newly-discovered commands/gotchas.

Step 1 — Detect

Scan the in-context conversation for observable failure/friction signals only:

  • Explicit user correction/redirect — "no, do X instead", "actually…", "that's not what I meant", "why did you…", reverting a decision. Highest-precision signal.
  • Ambiguous instruction that misled — a rule/CLAUDE.md/skill line was followed literally but wrongly; the guidance admitted a wrong reading.
  • Tool/test/build/lint failure caused by you — non-zero exits, failing typecheck/lint/ test/build traceable to your own change.
  • Loop / repeated retry — you tried the same thing multiple times, thrashed, or went in circles before it worked.
  • Revertgit revert / git checkout -- / undo of your own work.

For each signal found, extract an evidence bundle: the exact quoted turn(s) or command(s) that prove it happened.

Read the full file on GitHub · 136 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. 12d ago First seen · 136 lines · 87 tokens per session scan C daafe858fc58

Subscribe to this mod's changes

reflect is a skill published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 1,615 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.