What is percival-deep-research AGENTS.md?

A project-specific instruction file for the percival-deep-research repository. It records its formatting, test, patching, security, and Docker operating rules, but does not describe a general-purpose add-on.

Use it when working on that repository to run its tests and formatting checks, apply its patch script, preserve protections around external content, and interpret Docker operations.

It keeps work in that repository aligned with its existing checks and handling rules.

How bill-kopp-ai-dev/percival-deep-research configures Codex and OpenC

Reuse

Borrowing it

Nothing to install: this file belongs to bill-kopp-ai-dev/percival-deep-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bill-kopp-ai-dev/percival-deep-research/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bill-kopp-ai-dev/percival-deep-research

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md/github.svg)](https://agentmods.dev/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md"><img src="https://agentmods.dev/badge/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md"><img src="https://agentmods.dev/badge/instructions/bill-kopp-ai-dev/percival-deep-research/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 895 This file is loaded in full into every session.

When invoked 895 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00895	$0.00895
Opus 5.5	$0.00358	$0.00358
Sonnet 5.5	$0.00179	$0.00179
Haiku 4.5	$0.00089	$0.00089

Measured 6d ago against content hash c034d58edef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

percival-deep-research AGENTS.md 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 6d 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Owner and operating model

Bill Kopp ([email protected]) is the sole owner, operator, decision-maker, and signatory for this application and its IaC. The company is Positronic Bean Labs (PBLabs), website labs.positronicbean.com. Bill is the only person currently working on these projects.

A direct instruction or decision from Bill authorizes the work within its stated scope. Do not request a second approval, repeat an already recorded decision, or invent another owner/reviewer or handoff.
Keep process proportional: use one canonical source of truth and record evidence once per relevant source revision or image ID. Link to that evidence instead of duplicating it across plans and reports. Run only checks relevant to the changed risk; do not repeat equivalent checks as separate acceptance gates.
An instruction authorizes only its stated scope. Do not infer production changes or publication from approval of local work or a test rollout.
Before a runtime mutation, verify the target and its current image/configuration and preserve a practical rollback path. Use the owning manager and its supported interface; never edit manager state by hand. This is an operational safety check, not an additional approval gate.

Working conventions

Lint/format: uv run --with ruff ruff check . + uv run --with ruff ruff format ..
Tests: uv run pytest -q (coverage >=70% enforced by the canonical command itself, via addopts in pyproject.toml).
Patch gpt-researcher: run uv run python scripts/patch_gpt_researcher.py after each uv sync until upstream fixes NameError: name 'Any'. The script is a no-op for unaffected versions and refuses unsupported versions.
Research runs in an isolated worker process (percival_research/research_worker.py); the parent enforces the timeout and kills the worker. Do not move the pipeline back in-process.
Conventional Commits; scope = area afetada.
Preserve hardening in every change: external content remains wrapped in an XML envelope or prefixed with [SECURITY WARNING:...].

Read the full file on GitHub · 75 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.

6d ago Changed · +22 lines · +247 tokens per session c034d58edef4
8d ago Changed · +10 lines · +178 tokens per session fbf4ca5feda0
13d ago First seen · 43 lines · 470 tokens per session scan A 88ec59e68b00

Subscribe to this mod's changes

percival-deep-research AGENTS.md is an instructions file published in the GitHub repository bill-kopp-ai-dev/percival-deep-research (0 stars, last pushed 2d ago), licensed MIT. It adds 895 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-10-25.

percival-deep-research AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
percival-deep-research AGENTS.mdbill-kopp-ai-dev/percival-deep-research	Instructions file	0	2d ago	MIT	A	895	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

percival-deep-research: Instructions file for Codex