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 allemaar/open-skills --skill insight-retrogit clone --depth 1 https://github.com/allemaar/open-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/allemaar/open-skills/insight-retro)<a href="https://agentmods.dev/skills/allemaar/open-skills/insight-retro"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/insight-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/allemaar/open-skills/insight-retro"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/insight-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 | $0.00083 | $0.01519 |
| Opus 5.5 | $0.00033 | $0.00608 |
| Sonnet 5.5 | $0.00017 | $0.00304 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
insight-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 2mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro
Structured reflection after completing large implementations — map what changed, verify documentation accuracy, capture reusable patterns, update knowledge, and flag follow-up work.
Structured execution spec:
protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
Reflection Protocol — run after shipping significant work. Prevents knowledge loss, documentation drift, and tech debt accumulation. Observation only — fixes are separate tasks.
Phase 1 — Blast Radius Mapping
Identify everything that changed during execution. Sources: implementation_plan.md, walkthrough.md, task.md, conversation history, git diff.
Produce a structured manifest:
- Packages touched
- Apps touched
- Files created / modified / deleted
- New exports or APIs introduced
Group changes by package/app. This map drives every subsequent phase.
Gate: cannot proceed without knowing what changed.
Phase 2 — Pattern Extraction
Identify reusable patterns that emerged. Check for: new architectural patterns used in 2+ places; workarounds or gotchas future work will hit; integration patterns between packages not yet documented; novel solutions worth codifying.
For each pattern: name, description, reuse potential (HIGH / MEDIUM / LOW), recommended action (new skill, update existing skill, document in KI, or skip).
Phase 3 — Documentation Audit
For each package/app in the blast radius, audit all documentation surfaces.
Discovery: find README.md, llms.txt, index.yon, *.yon, *.feature.yon, CHANGELOG.md, barrel exports (index.ts).
- For docs/skills repositories: also check
SKILL.mdfiles (description quality, runtime parity), cross-reference maps between skills, per-skill front-matter consistency. Consider a full library-audit pass.
Sidecar audit: for each significant changed file (>100 LOC, public API, component/hook/route handler/schema) — does a colocated .yon exist? Still accurate? Should one be created?
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.
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.
- 2mo ago First seen · 128 lines · 83 tokens per session scan A ddcbedebe88a
insight-retro is a skill published in the GitHub repository allemaar/open-skills (15 stars, last pushed 24d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,519 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
notion
Search, read, create, and update Notion pages via the Notion MCP.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
create-stories
Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.