A session-review workflow that records mistakes, rework, corrections, and useful lessons in project files. Repeated mistakes can become permanent rules for future work.

It helps update error logs, project conventions, progress statuses, and agent guidance after a session.

It prevents the same problems from being forgotten and repeated in later coding sessions.

How lionshilov/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. 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/lionshilov/Forge/main/.claude/skills/forge-retro/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lionshilov/Forge

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lionshilov/forge/forge-retro/github.svg)](https://agentmods.dev/skills/lionshilov/forge/forge-retro)

Your own site

<a href="https://agentmods.dev/skills/lionshilov/forge/forge-retro"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lionshilov/forge/forge-retro"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 257 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00257
Opus 5.5	$0.00016	$0.00103
Sonnet 5.5	$0.00008	$0.00051
Haiku 4.5	$0.00004	$0.00026

Measured today against content hash 0c42e9d586ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forge-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 today.

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/forge-retro/SKILL.md · 17 lines

What it actually says

You are the Forge Orchestrator running a retrospective on this session.

Scan the conversation for: QA failures, wrong turns, rework, user corrections, and decisions that changed mid-flight.
For each real failure not yet logged, append a full ERR- entry to project_context/ERRORS_LOG.md (Agent / Task / Error / Root Cause / Fix / Prevention / Date).
If the same class of mistake happened twice or more (this session or already in the log), promote it to a permanent rule:
- a concrete ban in project_context/CONVENTIONS.md, or
- a new ❌ line in the responsible agent's agents/<name>/CLAUDE.md Anti-Patterns section.
Update project_context/PROGRESS.md statuses to match reality.
Report: what was logged, what was promoted to a rule, and one concrete suggestion for improving the workflow itself.

Do not invent failures to look thorough — an empty retro is a valid outcome.

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.

today First seen · 17 lines · 40 tokens per session scan A 0c42e9d586ae

Subscribe to this mod's changes

forge-retro is a skill published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 257 once invoked, about $0.0002 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 2026-11-07.

LLM Multi-Agent Project management ai-agents anthropic claude

forge-retro next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forge-retrolionshilov/Forge	Skill	5	1mo ago	MIT	A	40	Claude Code
requesting-code-reviewgraniet/kheish	Skill	213	today	Apache-2.0	A	41	Claude Code, Codex
google-workspacegraniet/kheish	Skill	213	today	Apache-2.0	A	40	Claude Code, Codex
jupyter-live-kernelgraniet/kheish	Skill	213	today	Apache-2.0	A	70	Claude Code, Codex
webhook-subscriptionsgraniet/kheish	Skill	213	today	Apache-2.0	A	24	Claude Code, Codex
notiongraniet/kheish	Skill	213	today	Apache-2.0	A	33	Claude Code, Codex
apple-remindersgraniet/kheish	Skill	213	today	Apache-2.0	A	17	Claude Code, Codex

Forge: Skill for Claude Code