retro-sync

retro-sync is a skill for Claude Code from MotWakorb/ai-agent-dev-team. It costs 55 tokens per session (865 once invoked), scanned A, original, MIT.

A tool for cleaning up local project retrospectives and pushing anonymized copies to a shared public GitHub repository. A retrospective is a written review of what went well, what failed, and what to change.

In plain words
What is it for?
Use it to scrub retrospectives, maintain a local mapping from real project names to pseudonyms, and publish the cleaned files to the shared repository.
Why use it?
It removes private project names and other identifying details before sharing lessons with other developers. It also keeps publishing separate from the tool that downloads the shared collection for analysis.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to scrub retrospectives, maintain a local mapping from real project…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/motwakorb/ai-agent-dev-team/retro-sync
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add MotWakorb/ai-agent-dev-team --skill retro-sync
Clone the repo
git clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-team

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-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro-sync.svg)](https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/retro-sync)
Your own site
<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/retro-sync"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 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 $0.00055 $0.00865
Opus 5 $0.00028 $0.00432
Sonnet 5 $0.00011 $0.00173
Haiku 4.5 $0.00006 $0.00086

Measured 6d ago against content hash f7ab1bfdf566, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

retro-sync 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scrub.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

retro-sync/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro Sync

Push local retros in ~/retros/ to the shared learning corpus: https://github.com/EndofLineTech/retros (public). Push-only — pulling the corpus down for analysis is /retro-mine's job. Retros are pseudonymized — the corpus is about process lessons, not about whose project it was.

Process

  1. Bootstrap (only if ~/retros is not already a git repo):

    git -C ~/retros init -b main
    git -C ~/retros remote add origin https://github.com/EndofLineTech/retros.git
    git -C ~/retros fetch origin
    
  2. Project map~/.claude/retro-project-map.txt holds stable pseudonyms, one real-name=pseudonym per line:

    acme-billing=project-a
    ai-agent-dev-team=project-b
    

    Check that every project referenced by the retros being synced has an entry. If one is missing, assign the next unused project-<letter> and append it. The map is local and private — never commit it, never mention real names in the retro repo. Ceiling: the map is per-machine; keep it consistent across your machines by copying it once (it changes rarely).

  3. Scrub — run the scrub script that lives next to this SKILL.md:

    bash <skill-dir>/scrub.sh ~/retros
    

    It applies, in place: project-map pseudonymization (content and filenames), then redaction of emails, IPs, private keys, common credential formats (AWS, GitHub, Anthropic/OpenAI, Slack, bearer tokens), then any literal strings in ~/.claude/retro-scrub.txt (one per line — client names, employer names, internal hostnames).

  4. Review — if the scrub redacted anything ([REDACTED], [EMAIL], key markers — pseudonym renames don't count), show the user what and where. A redaction hit means the retro-writing rules leaked something; name the category so the rules can be tightened.

  5. Commit and push (no hostnames or usernames in the commit message):

    git -C ~/retros add -A
    git -C ~/retros commit -m "retro sync: <n> retro(s)"
    git -C ~/retros pull --rebase origin main   # prerequisite for the push, not a gathering step
    git -C ~/retros push -u origin main
    

    Nothing staged and nothing unpushed → stop; there's nothing to sync.

Read the full file on GitHub · 58 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 58 lines · 55 tokens per session scan A f7ab1bfdf566

Subscribe to this mod's changes

retro-sync is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 865 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.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens