4a155afb63
- cognee section 67 → 30 lines: triggers and routing only, how-to lives in the plugin skill; recall/remember written as `cognee` subcommands - memory writes explicitly exempt from project write-confirmation rules; precedence for projects with their own findings convention (file first, cognee note with link) - removed-hook JSON dropped (in git history), one-targeted-retry rule added - ccc gotchas moved to the ccc skill, md paragraph translated and shortened - AGENTS-claude.md: onyx block no longer duplicates the plugin description Co-Authored-By: Claude Mythos 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HJuj5BdSLtn9R4xHduxYWY
3.3 KiB
3.3 KiB
@./AGENTS.md
Company knowledge (onyx & thicket)
- Company-knowledge questions go to the
onyxskill first (its description says when); its index surfaces pages that direct CQL/JQL misses. Always cite source links. - Two shortcuts past onyx: Thicket MCP for people lookups (role, team, email — its other sections are thin), Confluence CQL for precise lookups with known space/title.
- Same-topic follow-ups: use
onyx answer "..." --session <last session_id>.
Subagents
Default to delegating whenever the expected tool output exceeds the conclusion the main thread actually needs — multi-file research, log/data analysis, doc review, broad searches, verification runs. The session context is the scarce resource; a subagent burns its own context and returns only the result. Work inline only for single-fact lookups where file and symbol are already known — there, a subagent is pure overhead.
Use the Agent tool. Prefer specialized agent types over general-purpose
when one fits:
Explore— read-only search: locates code and facts (reads excerpts, not whole files). It does not review or audit; quality judgments stay with the parent or a dedicated reviewer.Plan— implementation strategy, architecture trade-offs.fork(subagent_type: "fork") — inherits the full conversation context, runs in the background, keeps its tool output out of the main thread. The tool of choice for "do X with everything you already know, give me only the outcome" — no need to re-explain state in the prompt.- Agent types not listed as available in the session (e.g. a
code-reviewer) don't exist there — check the available-types list instead of guessing.
Behavioral tier (MANDATORY — always set)
Prefix every Agent prompt with one of:
[TIER: FAST]— return raw results immediately; no internal monologue, no synthesis[TIER: STANDARD]— focused implementation logic; minimal preamble[TIER: DEEP]— complex reasoning; must conclude with a summary
Model selection (override only when needed)
Resolution order: explicit model param → agent type frontmatter → parent
inheritance. (fork always runs on the parent model; an override is ignored.)
- Don't override specialized agent types (
Explore,Plan, etc.) — their frontmatter is tuned. Leavemodeloff. - For
general-purposeunder an expensive parent (Opus/Fable): setmodel: sonnet— don't pay top rates for routine subagent work. - A bigger model (
opus) on a subagent only when isolated context and reasoning beyond what the parent can easily do inline are both needed. model: haikuonly for mechanical tasks: bulk classification, format conversion, summarizing pre-filtered text. Code-semantic work → Sonnet.
Context hygiene
- Prefer parallel
Explorecalls over sequentialgeneral-purposesessions; spawn independent agents in a single message so they run concurrently. - Once delegated, don't duplicate: never run the same search yourself while an agent is on it, and don't poll — results arrive as notifications.
- Follow-ups to an existing agent go via
SendMessage(keeps its context); a newAgentcall always starts fresh — right for unrelated lookups. - Summarize subagent findings in the main thread; the raw report is not shown to the user, so relay what matters.