What is spectre AGENTS.md?

Repository guidance for Spectre, a project whose canonical source files are transformed into generated Codex output. It explains which files to edit and which synchronization and verification commands to run.

Changing skills, subagents, hooks, installer behavior, or translation rules, then synchronizing and checking the generated Codex files.

It prevents agents from editing generated files directly and helps keep the shipped output consistent with the source.

How joenandez/spectre configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to joenandez/spectre. 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/joenandez/spectre/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/joenandez/spectre

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/joenandez/spectre/agents-md/github.svg)](https://agentmods.dev/instructions/joenandez/spectre/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/joenandez/spectre/agents-md"><img src="https://agentmods.dev/badge/instructions/joenandez/spectre/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/joenandez/spectre/agents-md"><img src="https://agentmods.dev/badge/instructions/joenandez/spectre/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 614 This file is loaded in full into every session.

When invoked 614 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	$0.00614	$0.00614
Opus 5.5	$0.00246	$0.00246
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 1mo ago against content hash 3e2c6ff62b8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spectre 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 1mo 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working in this repository.

Source Of Truth

plugins/spectre/ is the canonical plugin source.
plugins/spectre-codex/ is generated Codex output. Do not hand-edit it.
After changing canonical skills, agents, hooks, or plugin assets that ship to Codex, run:
```
npm run sync-codex -- --quiet
npm run sync-codex -- --check --quiet
```
If generated output is wrong, fix the canonical source or the translator under scripts/; do not patch plugins/spectre-codex/ directly.

Change Workflow

Check git status --short --branch before editing.
Identify the change type:
- workflow skill: edit plugins/spectre/skills/<skill>/SKILL.md
- subagent: edit plugins/spectre/agents/*.md
- learning/runtime helper: edit plugins/spectre/hooks/scripts/*
- Codex install/update behavior: edit src/ and load the project skill feature-codex-spectre-implementation first
- translator behavior: edit scripts/translators/* and scripts/sync-codex.cjs
Make changes only in the canonical source tree unless the target is installer or translator code.
Run npm run sync-codex -- --quiet.
Run npm run sync-codex -- --check --quiet.
Run the smallest relevant test command; use npm test when translators, installer behavior, or shared runtime helpers changed.
Review the diff. Generated plugins/spectre-codex/ changes are expected after sync; manual edits there are not.

Skill Editing Rules

Keep skills in compact contract form: Purpose, Inputs, Working Set, Outputs + DONE, Method/guardrails, Handoff, Escalate-If.
Prefer prompts that call focused prompts over duplicating another skill's body.
Keep dynamic data late-bound: branch names, diffs, file lists, and task paths should be read at runtime, not baked into skill text.
Preserve load-bearing gates explicitly: scope boundaries, destructive-operation guards, verification postconditions, DONE criteria, and no-suppression rules.
For skill rewrites or compression, use the spectre-rewrite-skill guidance as the quality bar before editing.

Read the full file on GitHub · 49 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.

1mo ago Changed · +6 tokens per session 3e2c6ff62b8c
2mo ago First seen · 49 lines · 608 tokens per session scan A fcc35de69a0d

Subscribe to this mod's changes

spectre AGENTS.md is an instructions file published in the GitHub repository joenandez/spectre (164 stars, last pushed 1mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0025 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 2026-08-30.

spectre AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spectre AGENTS.mdjoenandez/spectre	Instructions file	164	1mo ago	MIT	A	614	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	today	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

spectre: Instructions file for Codex