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.
npx skills add optimiziramsi/skills --skill retrogit clone --depth 1 https://github.com/optimiziramsi/skillsWrote 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/skills/optimiziramsi/skills/retro)<a href="https://agentmods.dev/skills/optimiziramsi/skills/retro"><img src="https://agentmods.dev/badge/skills/optimiziramsi/skills/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.
<a href="https://agentmods.dev/skills/optimiziramsi/skills/retro"><img src="https://agentmods.dev/badge/skills/optimiziramsi/skills/retro.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 | $0.00090 | $0.01122 |
| Opus 5 | $0.00045 | $0.00561 |
| Sonnet 5 | $0.00018 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro — route learnings, close the unit
This is how the instruction system self-updates without rotting. Harvest what this session taught, route each learning to the store that owns it, and keep the system lean.
Assumes the default .agent/ house layout: .agent/lessons/, .claude/rules/, .docs/,
.agent/handoff.md, .agent/instructions-changelog.md. A project on a different layout (e.g. keeps
docs/ at the repo root instead of .docs/) maps each to its own equivalent — the paths named in
these skills are the convention, not a hard requirement.
1. Harvest
Scan the session for durable learnings:
- user corrections ("no, do it this way"), confirmed conventions, owner decisions;
- bugs whose root cause implies a rule; gotchas that cost real time;
- a procedure that was wrong or missing.
Skip: session narration, one-off trivia, anything already recorded, secrets/personal data. A learning qualifies only if it would change how a future session acts — git history already holds the narrative.
2. Route each learning to its store
-
learning: Durable fact, gotcha, working agreement, engineering lesson store:
.agent/lessons/via: thelessonsskill -
learning: Binding rule (must / never) store: the project's binding-rule home —
.claude/rules/*.mdonly if the project uses that layer, else its canonical rule book / CLAUDE.md (never create a new instruction layer) via: add the enforcement tag; if you write[ENFORCED], the guard must exist — extend a hook in the same change, else tag it[HONOR] -
learning: Repeatable procedure that was wrong or missing store: the matching skill's steps via: edit the skill
-
learning: Architecture / code-shape / recipe store:
.docs/via: edit the doc -
learning: Volatile "where we left off" state store:
.agent/handoff.mdvia: thehandoffskill — NOT here -
learning: Enforcement gap (a checkable violation slipped through) store: a hook via: add / extend the guard
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.
- 9d ago First seen · 103 lines · 90 tokens per session scan A ac953e6d01c1
retro is a skill published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 90 tokens to every session and 1,122 once invoked, about $0.0005 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.