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 agentmods add skills/nicograef/handbook/reflectnpx skills add nicograef/handbook --skill reflectgit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/reflect)<a href="https://agentmods.dev/skills/nicograef/handbook/reflect"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/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 | $0.00074 | $0.01031 |
| Opus 5 | $0.00037 | $0.00515 |
| Sonnet 5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect
Workflow
1. Resolve scope
Argument: $ARGUMENTS
| Scope | Evidence | How |
|---|---|---|
| No argument (default) | the current session — the in-context conversation itself | Never read the session's own transcript file — it is already in context. Works on surfaces with no local transcripts. |
last N sessions |
the N most recent past session transcripts | Locate, cap, and summarize them per sources.md. One subagent per transcript, each returning problems, solutions, insights, and friction. |
last N commits, or an explicit revision range (e.g. v1.2..HEAD) |
git history | Per sources.md. Works in repos and on machines with no transcripts at all. |
2. Analyze the evidence
- Problems and issues that arose — errors, wrong turns, rework, misunderstandings.
- Solutions that worked — fixes, commands, approaches worth repeating.
- Notable insights — repo quirks, clarified conventions, facts worth remembering.
- Recurring friction — anything that slowed work down more than once.
3. Report in the chat
One chat report, fixed sections in this order: Problems & issues, Solutions found, Notable insights, Recurring friction. Each section is one bullet per entry.
- Empty section — one line, no padding.
- Chat only — never write a report file, journal, or reflections directory.
4. Derive plan items
Derive a short improvement plan from the report. Each item:
- Citation — the observation it derives from: report section plus entry.
- Category — memory, rule, skill, documentation, or tooling/process, per targets.md.
- Tie-break — when several categories fit, the most automatable wins.
- Target — its concrete file or directory, taken from the target map.
5. Dedup against existing artifacts
Before proposing, check each candidate for existing coverage:
- Per-category surfaces — see the target map in targets.md.
- Non-handbook repo — check the discovered artifacts from targets.md instead.
- Already covered — drop the learning.
- Covered, but the new evidence adds something — convert it into an update-proposal for the existing artifact.
- Never propose a duplicate.
What ships with it
2 files 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.
- yesterday Changed · -21 lines 69c7fa064191
- 5d ago First seen · 119 lines · 74 tokens per session scan A 09a6d9737a5d
reflect is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,031 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 2026-08-31.
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…