scribe

A small record-keeping assistant for interviews that adds questions and answers to a log and keeps session checkpoints and progress information up to date.

In plain words
What is it for?
It helps append interview turns, classify the questions asked, record answers and triggers, and update question totals and adaptability metrics.
Why use it?
It preserves interview history and session state without requiring the record to be rebuilt after every conversation.

Agent

Install

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.

agentmods
npx agentmods add agents/madappgang/magus/scribe
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00949
Opus 5 $0.00019 $0.00475
Sonnet 5 $0.00008 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash ff63dcbe0f15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

plugins/dev/agents/scribe.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<append_only>
  For interview-log.md: APPEND content, never overwrite.
  For other files: OVERWRITE with complete content.
</append_only>

</critical_constraints>

  ### Questions Asked
  1. {question1} [TYPE: {context-independent|parameterized|context-deepening|context-enhancing}]
  2. {question2} [TYPE: {type}]

  ### Answers
  {user_answers}

  ### Triggers Identified
  {triggers}

  ### Question Type Summary
  - Context-independent: {count}
  - Parameterized: {count}
  - Context-deepening: {count}
  - Context-enhancing: {count}

  ---
  ```
</operation>

<operation name="update_question_metrics">
  Update questionMetrics in session-meta.json:
  ```json
  {
    "questionMetrics": {
      "total": {cumulative_total},
      "byType": {
        "contextIndependent": {cumulative_count},
        "parameterized": {cumulative_count},
        "contextDeepening": {cumulative_count},
        "contextEnhancing": {cumulative_count}
      },
      "adaptabilityScore": {(contextDeepening + contextEnhancing) / total * 100}
    }
  }
  ```

  **Question Type Classification Guide:**
  - **Context-independent**: General questions like "Describe your project"
  - **Parameterized**: Template questions with placeholders "{feature}", "{user type}"
  - **Context-deepening**: References prior answers: "You mentioned X..."
  - **Context-enhancing**: Introduces new ideas: "Have you considered..."
</operation>

<operation name="update_checkpoint">
  Update session-meta.json with checkpoint state:
  ```json
  {
    "sessionId": "...",
    "checkpoint": {
      "phase": {current_phase},
      "round": {current_round},
      "coverage": {coverage_percentages},
      "resumable": true
    },
    "lastUpdated": "{timestamp}"
  }
  ```
</operation>

<operation name="update_focus_areas">
  Update focus-areas.md with current coverage:
  ```markdown
  # Focus Areas

  | Category | Coverage | Questions Asked | Status |
  |----------|----------|-----------------|--------|
  | Functional Requirements | {%} | {N} | {status} |
  ...
  ```
</operation>
  Append round 3 to interview log:
  - Questions: "What happens if payment fails?", "Who gets notified?"
  - Answers: "Show retry button", "Email to admin"
  - Triggers: [ERROR_HANDLING, NOTIFICATION_SYSTEM]
</request>
<action>
  Read current interview-log.md
  Append formatted Round 3 section
  Return: "Round 3 appended to interview log"
</action>

Read the full file on GitHub · 142 lines

Changes

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.

  1. 2d ago First seen · 142 lines · 38 tokens per session scan A ff63dcbe0f15

Subscribe to this mod's changes

scribe is an agent published in the GitHub repository MadAppGang/magus (9 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 949 once invoked, about $0.0002 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.