Start with 15 practical Markdown templates for instructions, Skills, architecture, design, specifications, plans, tasks, context, memory, tools, delegation, evals, safety, operations, and decisions. Every file includes fillable evidence fields, a decision rule, related guides, and primary references.
15
reviewed templates
4
lifecycle layers
24
primary references
30 days
maximum review interval
Every template inherits the evidence ledgers of its related reviewed topics.
A deterministic generator rebuilds files and integrity hashes when reviewed records change.
Coverage, links, frontmatter, word depth, bundle completeness, and SHA-256 hashes must pass.
Project files
Templates are starting contracts, not paperwork quotas. Remove inapplicable sections, replace every placeholder with evidence, and keep each file linked to the decisions and checks it supports.
Define project rules, desired behavior, implementation sequence, and bounded work.
AGENTS.md
Give coding agents the durable project map, commands, conventions, boundaries, and verification steps they need before changing the repository. Keep instructions concrete, scoped, and close to the files they govern.
SPEC.md
Turn an intended outcome into testable behavior, requirements, constraints, non-goals, edge cases, and acceptance evidence before selecting implementation details or decomposing the work.
PLAN.md
Translate an approved specification into a reversible technical approach, decision sequence, dependency-aware phases, validation strategy, deployment path, and rollback plan.
TASKS.md
Decompose the plan into dependency-ordered work units with explicit inputs, scope, outputs, acceptance checks, ownership, status, and integration evidence suitable for people or delegated agents.
Make the experience, system boundaries, context, and memory model explicit.
ARCHITECTURE.md
Describe system boundaries, responsibilities, data and control flow, trust zones, dependencies, failure behavior, and deployment topology so changes can be evaluated against an explicit operating model.
DESIGN.md
Design the human experience around bounded outcomes, visible system state, calibrated uncertainty, approval moments, recovery, and accessibility rather than treating the agent as an unrestricted chat box.
CONTEXT.md
Control which instructions, examples, tools, retrieved facts, messages, and summaries reach the model; record their authority, provenance, freshness, token cost, and intended decision.
MEMORY.md
Define what the system remembers across turns or runs, why each memory type exists, how identity and provenance are preserved, and how information is corrected, expired, deleted, and evaluated.
Contract tools, repeatable Skills, and delegation before agents take action.
SKILL.md
Package one bounded, repeatable workflow with a discoverable trigger, explicit inputs and outputs, ordered instructions, edge-case handling, and validation. Keep supporting references and scripts inspectable.
TOOLS.md
Inventory model-callable capabilities and make schemas, descriptions, authentication, authorization, side effects, idempotency, errors, timeouts, output limits, and approval requirements explicit.
DELEGATION.md
Define when work may be delegated, which specialized agents exist, what context and authority each receives, how handoffs are structured, and who verifies and synthesizes the returned work.
Gate releases with evaluation, safety, operations, and traceable decisions.
EVALS.md
Define representative tasks, outcomes, failure taxonomies, graders, human review, operational metrics, release thresholds, and regression processes for behavior that varies across models and environments.
SAFETY.md
Document threats, assets, identities, authority boundaries, least-privilege controls, approval policies, data protections, abuse cases, and incident response for agent behavior and tool use.
RUNBOOK.md
Give operators a tested path from alert to diagnosis, containment, rollback, recovery, communication, and follow-up using the signals and failure modes of the complete agent workflow.
DECISIONS.md
Keep important product, model, architecture, data, protocol, safety, and operating decisions traceable to context, alternatives, evidence, consequences, owners, and review triggers.