TRANSCRIPT

A saved record of a previous coding-agent session, including its messages, actions, and tool results.

In plain words
What is it for?
Review the recorded assignment work involving scanned pages, OpenCV boxes, and LaTeX files.
Why use it?
It preserves the session's working context so someone can inspect what was attempted and what information the agent used.

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/not-manu/annotate/transcript
Clone the repo
git clone --depth 1 https://github.com/not-manu/annotate
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 20,899 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 $0.00000 $0.20899
Opus 5 $0.00000 $0.10450
Sonnet 5 $0.00000 $0.04180
Haiku 4.5 $0.00000 $0.02090

Measured yesterday against content hash c52b06417aca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TRANSCRIPT 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.

examples/agents/TRANSCRIPT.md · 1,557 lines

How it starts

The opening of the file, as written. The whole thing — 1,557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCV bounding boxes for assignment

Session ID: ses_2ae037d74ffepwwadqLyaLHvcv Created: 4/3/2026, 2:16:36 AM Updated: 4/3/2026, 2:21:41 AM


User

Could you help me complete this assignment? Start by drawing boxes using OpenCV around where you think the answer's should be visually and then fill them in!


Assistant (Build · openai/gpt-5.4 · 5.1s)

Thinking:

Considering LaTeX assignment approach

I need to act on the workspace regarding LaTeX assignment examples and agents. First, I should inspect the repository before doing any substantial work and send an update. I might need to use todowrite since it's a multi-step task of more than three steps. I wonder if bash is necessary for the OpenCV script. I'll inspect the files and possibly use multi_tool_use.parallel for glob or read in bash. Let's start with a status and file listing.[REDACTED]

I’m locating the assignment source and page images first so I can place boxes against the scanned pages before editing the LaTeX.

Tool: glob

Input:

{
  "pattern": "**/*.{tex,pdf,png,jpg,jpeg,md}",
  "path": "/Users/manu/Documents/Projects/not-manu/annotate/examples/agents"
}

Output:

/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/img/page-03.png
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/img/page-02.png
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/img/page-01.png
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/homework-annotated.pdf
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/CLAUDE.md
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/AGENTS.md
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/pages/page-03.tex
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/pages/page-02.tex
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework/pages/page-01.tex
/Users/manu/Documents/Projects/not-manu/annotate/examples/agents/homework.pdf

Read the full file on GitHub · 1,557 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. yesterday First seen · 1,557 lines · 0 tokens per session scan A c52b06417aca

Subscribe to this mod's changes

TRANSCRIPT is an agent published in the GitHub repository not-manu/annotate (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 20,899 tokens. 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.

Related

Other agents, from other repositories

claim-verify

Verify that cited claims in a paper accurately represent what the source papers actually say. Checks every factual claim against its reference. Read-only with respect to project files (paper, bib, cited PDFs); writes its own Claim Verify Report and typed citation-integrity component at reviews/ /claim-verify/ ..…

flonat/flonat-research · 391 tokens

peer-reviewer

Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…

flonat/flonat-research · 352 tokens

code-review

Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…

flonat/flonat-research · 398 tokens

fatal-error-check

Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…

flonat/flonat-research · 180 tokens

redaccion-claude

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA). Versión de plantilla: 2.2.2 (2026).

jmrplens/TFG-TFM_EPS · 0 tokens

revisor-claude

Eres un tribunal académico experto en la evaluación de Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA). Versión de plantilla: 2.2.2 (2026).

jmrplens/TFG-TFM_EPS · 0 tokens