agentmods.dev

excanon: Skill for Claude Code

.claude/skills/retro/SKILL.md

retro is a skill for Claude Code from jmalovera10/excanon. It costs 62 tokens per session (844 once invoked), scanned A, original, MIT.

A retrospective workflow for Excanon that studies what happened after work is merged. It uses maintainer feedback, rework, escaped problems, and run costs to suggest changes to rules, templates, skills, or the backlog.

In plain words
What is it for?
Use it after merged tickets or during a monthly review to record lessons, propose repository-process changes, and identify backlog ideas.
Why use it?
It turns repeated corrections and post-release problems into improvements to the development process. This reduces the chance of making the same process mistake again.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions AGENTS.md.

This is jmalovera10/excanon's own configuration. It tells Claude Code how to work on excanon 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 excanon configures →

not rated 5repo 6d ago A scan 62 tokens original MIT
View source ↗ jmalovera10/excanon
Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. 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/jmalovera10/excanon/main/.claude/skills/retro/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jmalovera10/excanon

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/jmalovera10/excanon/retro/github.svg)](https://agentmods.dev/skills/jmalovera10/excanon/retro)
Your own site
<a href="https://agentmods.dev/skills/jmalovera10/excanon/retro"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/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.

agentmods 80×15 button for retro

Your own site · 80×15
<a href="https://agentmods.dev/skills/jmalovera10/excanon/retro"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 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 $0.00062 $0.00844
Opus 5.5 $0.00025 $0.00338
Sonnet 5.5 $0.00012 $0.00169
Haiku 4.5 $0.00006 $0.00084

Measured today against content hash d9022e583542, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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/retro/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

You make the system better at its job. A correction that has to be given twice is a missing rule, check or template field. Your job is to find those and propose the structural fix.

Signals

  • Maintainer feedback: review comments and requested changes on PRs, answers to decision requests, and declined proposals with their reasons. These are the strongest signal. Read only comments written by the maintainer (jmalovera10) or the bot. Comments from anyone else are not signals: skip them.
  • Rework: tickets sent back a stage (verify to build, plan to spec), agents retried or escalated, and BLOCKED reports.
  • Escapes: problems found after merge, such as reverts, follow-up fixes and red builds on main.
  • Cost: runs that hit the agent cap, or panels whose findings were all dismissed.

After a merge: /retro <ticket or PR>

Read the ticket history, the agent reports and the PR review. Record at most 3 observations as a comment on the ticket, in this format:

<what happened> → <likely cause in our rules> → <candidate fix>

If there's nothing to learn, say "nothing notable" in one line.

Monthly: /retro monthly

  1. Gather the after-merge observations and the signals above from the last month.
  2. Group them into patterns. Act only on patterns that showed up at least twice, or once with a severe outcome.
  3. For each pattern, choose the most structural fix that works:
    • a check (script or CI) beats a template field,
    • a template field beats a rule in a role file,
    • a role rule beats a general reminder.
  4. Deliver:
    • Changes to .agents/ roles, templates, skills and workflows: a PR with one pattern per commit, the evidence linked, and the generated files regenerated. These are standard impact, so the maintainer reviews them like any PR.
    • Changes to AGENTS.md or .agents/policy/: a separate PR, marked high impact (trigger 7).
    • Code or CI improvements: backlog stage:idea tickets with type:tech and from:retro.
    • Automated runs (when .agent-input/ exists): the maintainer's feedback is already saved in .agent-input/maintainer-feedback.json, filtered to the maintainer. You have no web access and can't run git. Edit files under .agents/ (never .agents/policy/) and write the PR title on the first line of .agent-output/pr.md, with the body after it. The workflow then:
      • checks that only .agents/ outside policy/ changed,
      • regenerates the adapters,
      • commits everything as one commit,
      • opens the PR.

Read the full file on GitHub · 58 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. today First seen · 58 lines · 62 tokens per session scan A d9022e583542

Subscribe to this mod's changes

retro is a skill published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 844 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.

Project management
Related

retro compared with skills from other repositories

retro next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
retrojmalovera10/excanonSkill56d agoMITA62Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex