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 yorrick/agent-skills --skill reflectgit clone --depth 1 https://github.com/yorrick/agent-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/yorrick/agent-skills/reflect)<a href="https://agentmods.dev/skills/yorrick/agent-skills/reflect"><img src="https://agentmods.dev/badge/skills/yorrick/agent-skills/reflect.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01078 |
| Opus 5 | $0.00035 | $0.00539 |
| Sonnet 5 | $0.00014 | $0.00216 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
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 6d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect
Analyze a session transcript to extract learnings and apply them as improvements to the project's documentation — CLAUDE.md, README.md, and auto-memory files.
What This Skill Does
After a session ends (or when invoked manually), reflect reads through the transcript and looks for:
- Corrections — The user said "no", "not like that", corrected output, or Claude had to retry something that failed
- Discoveries — New patterns, conventions, or constraints that emerged during the work
- Pain points — Workarounds, confusing APIs, tricky configurations that cost time
- Decisions — Architectural or design choices made during the session that future sessions should know about
Then it determines which project files would benefit from capturing these learnings and edits them directly.
Modes
Interactive Mode (default)
When a user runs /self-improve-skill:reflect in conversation:
- Summarize what happened in the session (2-3 sentences)
- List the learnings found, grouped by confidence (HIGH/MEDIUM/LOW)
- For each learning, show which file would be edited and the proposed change
- Ask the user to approve, modify, or skip each change
- Apply approved changes
Non-Interactive Mode (--non-interactive flag)
When invoked by the SessionEnd hook via claude -p "/self-improve-skill:reflect --non-interactive" < transcript.jsonl:
- Parse the JSONL transcript from stdin
- Analyze the session
- Apply only HIGH confidence changes directly
- Write MEDIUM/LOW confidence observations to the memory directory for later review
- Do NOT run any git commands
- Output a summary of changes made to stdout
Detect mode by checking if --non-interactive is present in the arguments.
Target Files
Only edit files within the current repository. Never edit global files like ~/.claude/CLAUDE.md.
CLAUDE.md
Add or update instructions that would prevent repeating mistakes or capture conventions discovered during the session. Examples:
- "Always run
npm run typecheckbefore committing — the CI check is strict" - "The
legacy/directory uses CommonJS, not ESM" - "Database migrations must be backwards-compatible (blue-green deploys)"
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.
- 6d ago First seen · 113 lines · 70 tokens per session scan A 564ae8baa1cb
reflect is a skill published in the GitHub repository yorrick/agent-skills (10 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,078 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.
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.