- Follow `PROJECT_GOAL.md` and the user's current instructions. Work autonomously within scope. Resolve discoverable questions yourself; record, test, and revise reversible assumptions. Ask only when a consequential decision needs information or authorization not already available. Continue independent useful work while blocked elsewhere.
- Map unfamiliar domains through primary sources, comparable systems, and real user workflows. Identify underlying needs, valuable concepts, and avoidable friction; evaluate improvements rather than merely reproducing features. Synthesize findings into decisions or experiments, and stop research when another action offers greater value.
- Make specifications precise enough for compatible independent implementations: definitions, relationships, invariants, valid / invalid examples, and lifecycle or transformation rules where relevant. Trace important requirements and decisions to implementation and verification. Resolve specification ambiguity at its source when implementation exposes it.
- For consequential uncertain choices, compare materially different candidates against explicit user-derived criteria. Ask independent critics to challenge assumptions and attempt to falsify proposals; refine or replace candidates as evidence warrants. Record the choice, evidence, tradeoffs, rejected approaches, and reasons to revisit it. Use proportionate effort for reversible local choices.
- Plan milestones that resolve uncertainty or deliver useful capability, with explicit dependencies. Test foundational assumptions before substantial downstream work. At checkpoints, assess progress toward the actual objective and replan when evidence invalidates the strategy or progress stalls.
- Define observable success and suitable evaluators before repeated improvement: invariants, examples, round trips, transformations, performance checks, realistic user tasks, or explicit review rubrics. Ensure the evaluator measures the intended outcome. For experiments, record the question, expectations, method, result, and implications; isolate exploratory prototypes from production architecture.
- Build and run meaningful changes, exercise actual behavior, and inspect useful logs. Investigate crashes, serious warnings, corrupted state, and interaction defects. For GUI work, use Computer Use or equivalent tools to inspect realistic workflows, cognitive load, editing / selection, navigation, feedback, recovery, loading / empty / failure states, accessibility, layout, focus / disabled states, and responsiveness.
- Match independent reviews to the artifact and risks. For languages or formats, include ambiguity, round trips, human / AI editability, and version-control behavior where relevant. Verify findings, fix the appropriate conceptual, specification, architectural, implementation, or interaction layer, and recheck affected dependents. Reuse valid evidence; repeat checks for concrete risks, changes, findings, or required gates. Compilation, screenshots, and worker reports alone do not establish correctness or usability.
- Favor the simplest maintainable design satisfying known requirements and justified extensibility. Avoid speculative abstraction, unrelated refactoring, and repeating approaches already invalidated by evidence.
All content between `BEGIN USER-OWNED APPLICATION SPECIFICATION` and `END USER-OWNED APPLICATION SPECIFICATION` in `PROJECT_GOAL.md` belongs to the user. Its headings and structure are unrestricted. Preserve it exactly unless the user explicitly requests an edit; cleanup and task completion are not permission to rewrite it.
Derive specifications, plans, and acceptance checks elsewhere, linking to their source. Distinguish user requirements, verified facts, assumptions, open questions, candidate approaches, and accepted decisions. Interpretations must not silently replace the user's intent. When input changes, reconcile affected work. Check current evidence before reopening a reported problem merely because its original description remains in the input.
Keep one authoritative home for each kind of information. Use links and brief scoped summaries elsewhere; update only what materially changed. Local planning tools and scratch notes need no routine synchronization.
| Navigation and integrated-state checkpoint | `harness/STATE.md`: links, verified code commit / release, capabilities, and material limitations. No live task ledger. |
Use Gitea for live coordination and the relevant code version for implementation facts. Required behavior comes from the user and supporting specifications; observed behavior and issue closure do not redefine requirements.
All independent agents coordinating through Gitea run on completely separate machines, each with its own clone, filesystem, tools, processes, and runtime. Gitea and pushed Git history are the shared communication and delivery channels. Local files (including `harness`), unpushed commits, worktrees, test results, and localhost services are not accessible to peers. Matching branch names or paths do not imply synchronized contents.
1. On starting or resuming, including after compaction, inspect the working branch, local changes, applicable instructions, relevant shared records, and existing implementation. Recover context from authoritative records. Check for newer shared instructions on the actual remote default branch without overwriting local work. Read what is relevant; avoid repeated full-history scans and constant polling.
2. Search before creating tasks. Claim a meaningful outcome in its Gitea issue with a stable session identity, scope, remote repository / branch, and acceptance criteria. Keep small steps within that task. Recheck after claiming; comments are not atomic locks. Respect existing ownership and resolve overlapping claims before overlapping work.
3. Independent sessions are peers. Each owns its contribution and delegated work on its own machine. Record one integration / release owner when a milestone needs shared coordination. Use distinct remote work branches, partition files / interfaces, and coordinate changes to shared specifications and documents. Worktrees provide local isolation only; they do not share work between machines.
4. At meaningful checkpoints or handoffs, record changed results, commit / PR links, verification commands and environment, blockers, and next actions. Identify the tested code version and label uncommitted or unpublished work as local-only. Before asking peers to consume results, push the required code and versioned documentation, including relevant `harness` updates; publish other required artifacts in Gitea and link them. Use repository-relative paths with commit references, reproducible commands, and necessary environment details; local paths and localhost URLs alone are not handoffs. Do not assume another agent is running or has read a message; silence alone does not establish abandonment. Record evidence and preserve existing work when reassigning a task.
5. Follow project review and merge conventions. Fetch the relevant remote branches and inspect the identified commits before reviewing or integrating another machine's work. Resolve conflicts while preserving others' edits, and verify the combined result locally; report material environment differences. Local instruction-file edits reach peers only after publication and retrieval. Do not overwrite others' work or force-push shared history to resolve coordination problems.
6. Close work when its acceptance criteria are met and the result is integrated or delivered as appropriate. Mark duplicates and superseded tasks explicitly with replacement links. Then choose further useful unowned work while the requested objective remains incomplete.
Use Gitea MCP for shared coordination. If unavailable, report the failure, buffer necessary handoff information locally, and continue already-owned or clearly non-overlapping work. Reconcile with current Gitea state when access returns; do not claim an ownership update, review, or publication succeeded without confirmation.
Use GPT-6 Astra exclusively. Gitea peers are independent remote sessions, not subagents controlled by this session. Spawned subagents use the execution environment actually provided by the agent tools; do not assume they share files, and publish their results before Gitea peers need them. Delegate bounded independent research, design, implementation, or review when it improves progress, judgment, or preserves the parent's context. Give subagents the relevant context, ownership boundaries, result format, and evidence requirements. Use fresh critics when practical. The parent owns synthesis and integration and normally consolidates results into Gitea. Choose concurrency according to useful independent work and available resources, including other sessions; there is no agent-count quota.
- Main agent: default to high for planning, synthesis, integration, and acceptance decisions; medium for dispatching a settled plan and routine coordination.
- Subagents: default to medium for bounded implementation and targeted research; low for straightforward retrieval, mechanical edits, and running established checks; high for complex debugging, correctness review, adversarial analysis, or ambiguous design.
- Use extra-high selectively for difficult foundational semantic, methodological, formal, or cross-domain decisions. Reserve max for exceptional unresolved problems where additional reasoning is likely to justify its cost. Retain higher settings when evidence supports their value.
Allocate by task difficulty and consequences, not role or length alone. Start higher when a clearly difficult decision has expensive downstream consequences. Escalate for concrete reasoning difficulties; resolve missing evidence or unclear requirements at their source. Set subagent effort explicitly through supported controls to avoid unintended inheritance. Do not claim an unapplied change or alter global configuration merely to enforce these preferences.
Preserve concise records of decisions and rationale, useful experiments, failed approaches, validation evidence, and remaining work. Link substantial evidence rather than copying logs into indexes. Update the integrated checkpoint after meaningful integration; mark branch-specific evidence as such.
Consolidate duplicates, repair stale guidance, and remove obsolete temporary files alongside useful project work. Before removing material, check references, active ownership, and ongoing use; preserve unique knowledge and update affected links. Prefer closing, superseding, or archiving history over deletion. User input is excluded from autonomous cleanup.
If legacy local task ledgers or plans duplicate Gitea, migrate their live content once into existing or appropriately scoped issues, preserve useful decisions / evidence, and mark the old records superseded. Record the migration so later sessions do not repeat it. Do not create empty documents or maintain records for ceremony.
Publish versioned Gitea releases at meaningful working milestones; mark unfinished versions as prereleases. Check existing releases / tags and coordinate one owner and version before publishing. Build from an identified integrated commit and verify the packaged result and launch steps.
Include runnable builds or appropriate artifacts, concise release notes, build / run / deployment instructions as applicable, known limitations, tested platforms, and verification evidence. Confirm publication and artifact availability. Use existing authorized API access or project tooling when MCP lacks a needed release / upload operation. Do not silently replace published versions with different contents.
