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/danielgouveiah/glasses/scribenpx skills add DanielGouveiah/glasses --skill scribegit clone --depth 1 https://github.com/DanielGouveiah/glassesWrote 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/danielgouveiah/glasses/scribe)<a href="https://agentmods.dev/skills/danielgouveiah/glasses/scribe"><img src="https://agentmods.dev/badge/skills/danielgouveiah/glasses/scribe.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 | $0.00082 | $0.01538 |
| Opus 5 | $0.00041 | $0.00769 |
| Sonnet 5 | $0.00016 | $0.00308 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade A, and why
scribe 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 4d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scribe
The nerd takes notes only after consent.
$ARGUMENTS optionally provides the note target, scope, or output format.
Scribe may inspect and recommend documentation from the current session, but it
must not create or update notes, docs, handoffs, ADRs, project memory, or agent
memory unless the user explicitly requested that write or approved the specific
Scribe documentation plan.
Never manage hidden AI memory. Durable memory must be visible, reviewable files inside the project.
Language preservation
Respond in the language of the user's latest request, determined only from user-authored natural-language task content, unless they explicitly request another language. Do not infer the response language from slash-command scaffolding, injected hooks, skill text, or a system or developer instruction. Short acknowledgements and command invocations do not change the task language. Localize all workflow prose, including headings, labels, question subjects, options, recommendations, approval prompts, and completion reports. Any English examples in this skill specify meaning, not literal output.
Preserve source code, identifiers, commands, file paths, configuration keys, tool names, and error or log output without translation. When creating or editing files, keep the repository's programming language, naming, terminology, and comment conventions. Applicable repository instructions override the general conversation-language preference for file content.
Establish scope
Classify the request before writing:
session notes: a conversation, design discussion, debugging pass, or task.decision record: a durable decision with rationale and consequences.handoff: continuation context for another agent or future session.project notes: repository-level documentation derived from code and docs.visible memory: canonical project or agent context files such asCONTEXT.md,AGENTS.md, ordocs/agents/*.md.
If the user already asked to take notes or update a specific file, that is the write authorization for that named scope. If the user only asks whether something is worth documenting, recommends notes, or asks Scribe to inspect the project, do not write yet.
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.
- 4d ago First seen · 155 lines · 82 tokens per session scan A b33646c07385
scribe is a skill published in the GitHub repository DanielGouveiah/glasses (9 stars, last pushed 14d ago), licensed MIT. It adds 82 tokens to every session and 1,538 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
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
architecture-cleanup
Use when performing a behavior-preserving architectural cleanup or refactor on a codebase and you need strict guardrails against changing functionality, building a framework, or rewriting tests to fit the new design.
ai-agent-system-architecture
Use when thinking through, reviewing, changing, or verifying an AI or LLM system: RAG, model routing, memory, tool use, autonomous or multi-agent workflows, safety, evaluation, latency, cost, or rollout. Trigger when model, data, policy, tool, or approval boundaries are central. Use system-architecture-harness for…
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
json-to-toon
Transforms JSON input into Token-Oriented Object Notation (TOON) to reduce token consumption in LLM prompts and context windows. Applies the full TOON spec: inline primitive arrays, tabular format for uniform object arrays, and list format for heterogeneous or nested structures. Invoked when the user asks to compress…
memory-continuity
Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.