Skip to content
Back to skills

Agent Context

ASecurity

Rules shared by wipnote agents: work attribution, safety rules, research routing, truncation-resilient reporting. Preloaded into coder agents via skills:.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 19, 2026
ai-agentsgobashgitapi

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Scanned October 19, 2026

npx -y skills add shakestzd/wipnote --skill agent-context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Context?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agent Context
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/shakestzd-agent-context/badge)](https://www.skillsdirectory.com/skills/shakestzd-agent-context)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agent-context
description: "Rules shared by wipnote agents: work attribution, safety rules, research routing, truncation-resilient reporting. Preloaded into coder agents via skills:."
user-invocable: false
---

# Shared Agent Context

## Work attribution and completion

Use the work item ID from your task prompt (e.g. "Feature: feat-580dc00b") with `wipnote feature start <id>` (or `bug`/`spike`); do not create a new one. With no ID, run `wipnote relevant "<topic>"` first (it searches completed tracks, plans and features too) and create an item only if nothing covers the scope. Bugs need an owning track; `--standalone` is for features only. When your gate passes, run `wipnote <kind> complete <id>` before reporting back. If wipnote is unavailable, proceed and report.

## Safety

- Never edit `.wipnote/` files directly; use the CLI. Plan YAML goes through `wipnote plan rewrite-yaml <plan-id> --file <tmp>` (validates and writes atomically).
- Batch wipnote CLI calls with `&&`; each Bash call costs a turn. Split only when a later command needs an earlier one's output.
- Run `wipnote arch resolve --for <work-item-id>` once at start; treat `UNVERIFIED:` cards as advisory and verify in code.

## Research routing

- **For coder and researcher agents:** external libraries, harness contracts and API details go to web search/fetch and `gh search issues`/`gh api` first; official docs, issues and changelogs are first-class research. Search for a maintained package before building, and record the adopt-vs-build outcome.
- **For orchestrators:** Research-first does not mean orchestrator researches directly; dispatch a sidecar (native Explore or the Codex `explorer` role for code, `researcher` for docs and on Antigravity). Main-context `web.*` use is limited to explicit user browse requests, one-shot verification with no sidecar, or confirmation after a sidecar failure.
- This repo's own code: local search first. Verify any local assumption about external behaviour against official docs.

## Persist, then summarize

Final reports get truncated, so persist substance first: findings via `wipnote <kind> set-description <id> "..."`, progress via `wipnote <kind> add-step <id> "..."`, durable facts via `wipnote arch add`, code via `git commit` (only when your task includes committing and the gate passes). On long tasks (>30 calls) persist incrementally. The final message is a compact summary pointing at those artifacts.

## Writing style

Write final reports, `set-description` and `add-step` text in plain English (ASD-STE100-lite): one idea per sentence, sentences under 20 words, active voice, commands for steps, one word for one meaning. Code, commands, paths and quoted output stay exact. The main-conversation equivalent is the `wipnote:Plain English` output style; output styles do not reach subagents, so this section is the rule here.

## Principles

DRY, single responsibility, KISS, YAGNI; functions <50 lines, files <500. Prefer CLI over skills over deferred MCP tools. Never author or overwrite a project's AGENTS.md, CLAUDE.md, or GEMINI.md.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.