agent-context
Shared agent context — work attribution, safety rules, and development principles. Loaded by all plugin agents via skills: frontmatter.
What this skill does
# Shared Agent Context
## Work Attribution
The orchestrator always provides the work item ID in your task prompt (e.g., "Feature: feat-580dc00b"). Use it:
```bash
wipnote feature start <id> # or bug start / spike start
```
**Rules:**
1. Look for a feature/bug/spike ID in the task prompt first
2. If found, run `start` on it — do NOT create a new one
3. Only create a new work item if the prompt genuinely contains no ID
4. If wipnote is unavailable, proceed — attribution is not a blocker
## Work Completion
When your task is done and quality gates pass:
1. Run `wipnote feature complete <id>` (or `bug complete`, `spike complete`)
2. Do this BEFORE reporting back to the orchestrator
3. If the CLI is unavailable, report completion — the orchestrator will handle it
## Safety Rules
**FORBIDDEN:** Never edit `.wipnote/` files directly. Use the CLI:
- `wipnote feature complete <id>` not `Edit(".wipnote/features/...")`
- `wipnote bug create "title" --track <trk-id>` not `Write(".wipnote/bugs/...")`
Bugs require an owning track: use `wipnote relevant "<topic>"` or `wipnote track list` to find one before creating the bug. `--standalone` is supported for feature creation only, not bug creation.
**BATCH wipnote CLI calls.** Each Bash tool call spends one turn from the user's quota. Chain commands with `&&` into a single invocation whenever possible. Do this (1 call):
```bash
wipnote bug create "A" --track trk-xxx && \
wipnote bug create "B" --track trk-xxx && \
wipnote link add feat-aaa bug-new --rel caused_by
```
Never 3 separate Bash calls for the same thing. Only break into multiple calls when a later command must parse the output (e.g., a returned ID) of an earlier one.
### Plan YAML Updates
Plan YAML files (`.wipnote/plans/*.yaml`) are validated assets — never write them directly.
Use the CLI to ensure valid structure:
- **Create:** `wipnote plan create-yaml "<title>"`
- **Update:** `wipnote plan rewrite-yaml <plan-id> --file /tmp/updated.yaml`
- **Validate:** `wipnote plan validate-yaml <plan-id>`
The `rewrite-yaml` command validates schema, checks meta.id match, and writes atomically.
Agent workflow: read plan → modify in memory → write to temp file → call rewrite-yaml.
## Research routing — where does the answer live?
Before grepping local code, route by where the answer actually lives:
- External libraries/SDKs, upstream harness behavior (Claude Code / Codex / Gemini CLI), third-party tool error messages, version/API contracts, or "is this a known/recent issue?" → use your web search / web fetch tools and the GitHub CLI (`gh search issues`, `gh api`) FIRST, or in parallel with local search. Official docs, GitHub issues, releases, and changelogs are first-class research, not a last resort.
- This repo's own code, conventions, wiring, or "where is X defined?" → use local file-read/search tools first.
- When local code encodes an assumption about EXTERNAL behavior, verify it against official docs before trusting it.
Web/docs/GitHub searches COUNT as research — don't reflexively fall back to local grep for questions whose answer lives upstream.
## Development Principles
- DRY — check for existing utilities before creating new ones
- SRP — one purpose per function/module
- KISS — simplest solution that satisfies requirements
- YAGNI — only implement what is needed now
- Module limits: functions <50 lines, files <500 lines
- Research existing libraries/packages before implementing from scratch
- Check project dependencies before adding new ones
These principles are language-neutral and apply to any codebase.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.