ai-agent-rules-generator doc-sync.instructions.md

Instructions for keeping documentation aligned with code changes. They define which documents to update and require user verification before documentation updates.

In plain words
What is it for?
Guiding documentation updates for files under includes/ and enforcing the stated verification steps.
Why use it?
They reduce the risk of code changes being merged while the related documentation is outdated or updated too early.

Instructions file for GitHub Copilot

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 instructions/savedpixel/ai-agent-rules-generator/doc-sync
Clone the repo
git clone --depth 1 https://github.com/savedpixel/ai-agent-rules-generator

Made for: GitHub Copilot.

Per session 1,652 This file is loaded in full into every session.
When invoked 1,652 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01652 $0.01652
Opus 5 $0.00826 $0.00826
Sonnet 5 $0.00330 $0.00330
Haiku 4.5 $0.00165 $0.00165

Measured 2d ago against content hash e1d17bff9a21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agent-rules-generator doc-sync.instructions.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **Visual Verification Gate** — If the work affects front-end/UI/visual elements, you opened a browser, took screenshots, and visually confirmed (see `task.instructions.md` → Visual Verification Gate). HTML inspection,
examples/glitch-payment-gateway/v1.1/copilot/generated/.github/instructions/doc-sync.instructions.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Sync Rules

These rules apply when modifying files under includes/. They define which documentation to update and when.


MANDATORY: Auto-Update Documentation

Whenever you implement changes, you MUST update the relevant documentation files. Never skip this step. If you are unsure which docs to update, consult the Documentation Trigger Map below and ask the user if needed — do not skip doc updates because you're uncertain. Only the user may waive documentation requirements.

Documentation Timing Gate (BLOCKING — requires user verification first)

You may NOT update documentation, update task logs, or perform any batch-boundary step until ALL of the following gates have passed in order:

  1. Agent Self-Evaluation Gate — You confirmed this is the best solution (see task.instructions.md → Agent Self-Evaluation Gate).
  2. Visual Verification Gate — If the work affects front-end/UI/visual elements, you opened a browser, took screenshots, and visually confirmed (see task.instructions.md → Visual Verification Gate). HTML inspection, DOM queries, and curl do NOT count.
  3. User Verification Gate — The user has either tested and confirmed, OR explicitly waived testing (see task.instructions.md → User Verification Gate).

If the user has not yet responded to the verification prompt, you may NOT:

  • Edit any file in docs/
  • Edit any file in docs/task/logs/
  • Edit any file in docs/agent-observations/
  • Stage, commit, or push any changes

Scenario Evidence Requirement (BLOCKING): Documentation is blocked until all required behavior-path scenarios were executed end-to-end.

Untested Disclosure Requirement (BLOCKING): The verification summary must include an explicit Not Tested section listing every unexecuted check/scenario (or Not Tested: none).

CRITICAL — NO SKIPPING: You are never permitted to bypass this timing gate on your own judgment.

Update "Last updated" Date on Every Doc Edit

Whenever you edit any markdown file in docs/, you MUST also update its > **Last updated:** YYYY-MM-DD line (or <!-- Updated: YYYY-MM-DD --> comment) to today's date.

Read the full file on GitHub · 196 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 · 196 lines · 1,652 tokens per session scan A e1d17bff9a21

Subscribe to this mod's changes

ai-agent-rules-generator doc-sync.instructions.md is an instructions file published in the GitHub repository savedpixel/ai-agent-rules-generator (7 stars, last pushed 4mo ago), licensed MIT. It adds 1,652 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

copilot-setting AGENTS.md

AGENTS.md instructions for zexion7873/copilot-setting, covering copilot-setting — agent guide, communication language, repository purpose, validation commands and architecture.

zexion7873/copilot-setting · 2,786 tokens

copilot-setting java.instructions.md

Load when writing or reviewing .java code — Java 8 version-lock floor: syntax, exceptions, logging, concurrency. Triggers on: var, records, text blocks, List.of/Map.of, pattern matching, java.time, BigDecimal, SLF4J. Forces Java 8, not modern Java. Defer SQL/Spring/JSP to their files.

zexion7873/copilot-setting · 1,326 tokens

copilot-setting spring-hibernate.instructions.md

Load when writing or reviewing Java or hbm.xml on a Spring 3.2 + Hibernate 4.2 stack — native Session API, XML mappings/tx, Spring MVC. Triggers on: getCurrentSession (not openSession), hbm.xml (not JPA @Entity), (not @Transactional), @Controller/@RequestMapping (not @GetMapping). No Spring Boot/JPA. Defer SQL to…

zexion7873/copilot-setting · 1,366 tokens

copilot-setting sql-ddl.instructions.md

Load when writing or reviewing MySQL DDL or migration scripts — CREATE/ALTER TABLE, indexes, stored procedures, backfills. Triggers on: ALTER TABLE, ALGORITHM=INSTANT/INPLACE, online schema change (pt-osc, gh-ost), rollback scripts, chunked backfill, DROP COLUMN, sp stored procedures. MySQL 8.0 / InnoDB. Query and…

zexion7873/copilot-setting · 989 tokens

copilot-setting xml-config.instructions.md

Load when writing or reviewing stack XML — Spring applicationContext, hbm.xml, web.xml, or Maven pom.xml. Triggers on: (not ), spring-beans-3.2.xsd (not 4.0), , DispatcherServlet, , scope test/provided, source/target 1.8, no -SNAPSHOT/LATEST. No Spring Boot. Defer SQL/Java to their files.

zexion7873/copilot-setting · 924 tokens

copilot-setting sql.instructions.md

Load when writing or reviewing SQL in Java code — JDBC DAOs, HQL, query tuning. Triggers on: PreparedStatement/? (no concat), :paramName, no SELECT , WHERE on UPDATE/DELETE, indexes, EXPLAIN. Raw JDBC, not Spring Boot. DDL/migrations: sql-ddl.instructions.md. Defer Hibernate queries to spring-hibernate.instructions.md.

zexion7873/copilot-setting · 732 tokens