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 KaimingWan/oh-my-kiro --skill omk-self-reflectgit clone --depth 1 https://github.com/KaimingWan/oh-my-kiroWrote 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/kaimingwan/oh-my-kiro/omk-self-reflect)<a href="https://agentmods.dev/skills/kaimingwan/oh-my-kiro/omk-self-reflect"><img src="https://agentmods.dev/badge/skills/kaimingwan/oh-my-kiro/omk-self-reflect/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/kaimingwan/oh-my-kiro/omk-self-reflect"><img src="https://agentmods.dev/badge/skills/kaimingwan/oh-my-kiro/omk-self-reflect.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 | $0.00912 |
| Opus 5 | $0.00042 | $0.00456 |
| Sonnet 5 | $0.00017 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
omk-self-reflect 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger Examples
- "记住，以后都要这样做"
- "always use jq for JSON, never sed"
- "@reflect 把这个教训沉淀一下"
- "I told you this before, capture it"
- "这个错误犯了好几次了，升级成规则"
Self-Reflect — Agent Self-Learning System
Scope (v3)
-
Promotion execution: When hook outputs 🔥 or ⬆️, read episodes.md, distill into 1-2 line rule, propose to user, write to rules.md if approved. Mark source episodes as
promoted. -
Complex insight capture: When hook outputs 🚨 (complex) and the correction is too complex for auto-capture (no simple DO/DON'T pattern), help user articulate and write to episodes.md via the same format.
NOT responsible for: daily capture (hook does it), dedup (hook does it), quality reporting (hook does it).
Sync Targets
| Scenario | Target |
|---|---|
| Top-level principle (user approved) | AGENTS.md / CLAUDE.md (Principles section) |
| Promotion (≥3 same pattern) | knowledge/rules.md (matching keyword section) |
| Complex insight | knowledge/episodes.md |
| Code-enforceable rule | .kiro/rules/enforcement.md |
Writing to Protected Files (AGENTS.md / CLAUDE.md / .claude/rules/)
When user explicitly approves writing to a protected instruction file, agent MUST autonomously execute the full three-step flow — do NOT wait for the human to do it manually:
touch .skip-instruction-guard- Write the change
rm -f .skip-instruction-guard
This bypasses the pre-write hook temporarily. Only do this when user has clearly approved the content in the current conversation.
Episode Format
DATE | STATUS | KEYWORDS | SUMMARY
- DATE: YYYY-MM-DD
- STATUS: active / resolved / promoted
- KEYWORDS: 1-3 english technical terms, ≥4 chars, comma-separated
- SUMMARY: ≤80 chars, no
|character, actionable DO/DON'T
Promotion Process
- Read episodes.md, find keywords appearing ≥3 times in active episodes
- Distill into 1-2 line rule with DO/DON'T + trigger scenario
- Read knowledge/rules.md section headers (
## [keywords]) - Clustering — choose target section by semantic match:
- Compare episode keywords with each section's keyword list
- Pick the section with most keyword overlap + semantic relevance
- If no section matches → create new
## [episode-keywords]section at end of file - If placing in existing section → append new keywords to section header if they add value
- Propose to user for approval (show target section)
- If approved: append rule to chosen section, change source episodes status to
promoted - Output: ⬆️ Promoted to rules.md [section]: 'RULE'
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.
- 12d ago First seen · 92 lines · 83 tokens per session scan A cff2d97672e1
omk-self-reflect is a skill published in the GitHub repository KaimingWan/oh-my-kiro (103 stars, last pushed 5mo ago), licensed MIT. It adds 83 tokens to every session and 912 once invoked, about $0.0004 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 2026-08-30.
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.