Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. 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/design-and-deliver/claude-code-autoconfig/main/.claude/agents/create-retro-item.mdgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/agents/design-and-deliver/claude-code-autoconfig/create-retro-item)<a href="https://agentmods.dev/agents/design-and-deliver/claude-code-autoconfig/create-retro-item"><img src="https://agentmods.dev/badge/agents/design-and-deliver/claude-code-autoconfig/create-retro-item/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/agents/design-and-deliver/claude-code-autoconfig/create-retro-item"><img src="https://agentmods.dev/badge/agents/design-and-deliver/claude-code-autoconfig/create-retro-item.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00058 | $0.00548 |
| Opus 5.5 | $0.00023 | $0.00219 |
| Sonnet 5.5 | $0.00012 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
create-retro-item 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.
What it actually says
You write retro story files for this repository. The caller hands you one improvement
opportunity; you turn it into a single, fully-scoped Markdown file under .claude/retro/
and report the path. You do not fix the problem, and you do not touch any other file.
What the caller gives you
- title — short descriptive name; it becomes the filename
- problem — what is wrong, or what friction was hit
- criteria — specific, testable acceptance criteria
- approach — how to fix it
- priority — Critical | High | Medium | Low
- effort — S | M | L | XL
- files — the files involved, with line numbers when known
If a field is missing, infer it from the others and mark it (inferred) rather than asking.
Steps
- Slug the title: lowercase, ASCII kebab-case,
.mdextension (flaky-poll-timer.md). - Check for a duplicate:
Glob.claude/retro/*.md, thenReadany file whose name shares two or more words with the slug. If one already covers this problem, do not write a new file — reply with that path and one line on how it overlaps. Writethe file using exactly this template:
# [Title]
## Problem
[Problem description]
## Acceptance Criteria
- [ ] [Criteria 1]
- [ ] [Criteria 2]
## Approach
[How to fix]
## Priority
[Priority level]
## Effort
[Effort size]
## Files
- [file1]
- [file2]
- Reply with one line:
Created .claude/retro/<slug>.md(or the duplicate's path).
Guidelines
- Concise: actionable descriptions, not essays.
- Specific: real file paths and line numbers when you have them.
- No duplicates: step 2 is not optional.
- Never block: no clarifying questions — write the item with what you were given.
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 Changed · +2 lines · +58 tokens per session c9551e70aec3
- 1mo ago First seen · 63 lines · 0 tokens per session scan A 69ab5a688062
create-retro-item is an agent published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 548 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 2026-09-05.
Other agents, from other repositories
task-planner
Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
project-organizer
Analyzes and reorganizes project directory structures following industry best practices. Cleans up old files, logs, and redundant code. Handles Python, JavaScript, and general software projects with git integration.
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
hooks-daemon-plan-dedupe-scout
Before a new plan is filed, check whether an existing plan already covers the same work. Read-only; reports candidates with reasons, never a verdict.
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
staff-software-engineer
Engineering orchestrator. Runs the full pipeline (plan, dev, test, pr) for a feature, picking the right area skill (backend, web, mobile, devops). Use via Task tool for delegation, or /sse:run for direct invocation.