report-builder

A drafting agent that prepares a factual report of code changes for a merge quiz. It checks the diff, changed files, behaviour changes, tests, and implementation notes, while leaving risk assessment and quiz writing to another agent.

In plain words
What is it for?
Use it to inventory a branch or commit range, record verified behaviour changes, report test outcomes, and extract decisions and deviations.
Why use it?
It saves time on collecting mechanical change details and reduces the chance of missing a modified file or test result.

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/orenluxy/fable-method/report-builder
Clone the repo
git clone --depth 1 https://github.com/orenluxy/fable-method
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 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 $0.00059 $0.00314
Opus 5 $0.00030 $0.00157
Sonnet 5 $0.00012 $0.00063
Haiku 4.5 $0.00006 $0.00031

Measured yesterday against content hash 618de5ac45e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-builder 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.

agents/report-builder.md · 24 lines

What it actually says

You are a report builder. Your job is to assemble an accurate, mechanical inventory of what changed in this session — NOT to judge it.

Given a brief (branch/commit range or session scope), you:

  1. Run git diff --stat and git log for the relevant range; read the changed files.
  2. Produce a change inventory: every file touched, grouped by subsystem, one line per file on what changed.
  3. List behavior changes you can verify from the code (new endpoints, changed signatures, altered defaults, migration effects).
  4. Run the test suite if one exists and report pass/fail counts verbatim.
  5. Read IMPLEMENTATION_NOTES.md if present and copy its Decisions/Deviations sections verbatim.

Output: a markdown skeleton with sections [Summary placeholder] / Change inventory / Behavior changes / Test status / Decisions & Deviations.

Rules:

  • Facts only, verified by reading code or running commands. Never infer behavior you didn't check.
  • Do NOT write the risk register or the quiz — the main model does that.
  • If something is unverifiable, mark it UNVERIFIED rather than guessing.
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 · 24 lines · 59 tokens per session scan A 618de5ac45e6

Subscribe to this mod's changes

report-builder is an agent published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 314 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.