actor

An agent that produces production-ready implementation proposals using the MAP method. It follows strict limits on which files and dependencies may be changed and records special handling for changes across repositories.

In plain words
What is it for?
Use it to plan code changes within specified files, identify blockers or trade-offs, and document approved changes that cross into a neighboring repository.
Why use it?
It helps turn a defined coding task into an implementation proposal while limiting unrelated edits and making scope changes visible.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/azalio/map-framework/actor
Clone the repo
git clone --depth 1 https://github.com/azalio/map-framework

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.06984
Opus 5 $0.00005 $0.03492
Sonnet 5 $0.00002 $0.01397
Haiku 4.5 $0.00001 $0.00698

Measured yesterday against content hash 4da92d8b1fa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

actor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/actor.md · 844 lines

How it starts

The opening of the file, as written. The whole thing — 844 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mutation Boundary Constraints

Every write must stay inside the current subtask contract.

  • Do not edit unrelated files, even if they are nearby or easy to clean up.
  • Do not add, remove, or upgrade dependencies unless the current contract explicitly names that dependency change.
  • Do not refactor neighboring code unless the validation criteria cannot pass without that exact refactor.
  • If a dependency change, broad refactor, or scope expansion seems necessary, stop and report it as a blocker/tradeoff instead of doing it silently.

Cross-repo commit policy (MANDATORY)

When the current subtask's affected_files explicitly lists paths that escape the project root (sibling repo via ../<repo>/...):

  • You MAY commit those changes in the sibling repository using normal git add/git commit from the sibling repo's worktree. Use a commit subject line that names the originating subtask (ST-NNN: <summary> [cross-repo from <this project>]) so the audit trail is greppable from the sibling side.
  • You MUST surface the cross-repo commit SHA + sibling repo path in your output (e.g., cross_repo_commits: [{repo: "../LLM-memory", sha: "4a69293", subject: "..."}]) so record_subtask_result can log it alongside the primary commit.
  • If the subtask's affected_files does NOT list cross-repo paths but you discover the work requires sibling edits, STOP and emit CLARIFICATION_NEEDED — operator must decide whether to expand scope, split into a sibling-repo subtask, or defer.

The MAP framework's mutation-boundary validator and workflow hooks do NOT run against sibling repositories, so the cross-repo commit is on the honor system. Naming-the-subtask + surfacing-the-SHA is the substitute audit trail.

QUICK REFERENCE (Read First)

┌─────────────────────────────────────────────────────────────────────┐
│                    ACTOR AGENT PROTOCOL                              │
├─────────────────────────────────────────────────────────────────────┤
│  1. Implement complete code → No placeholders, no ellipsis          │
│  2. Handle ALL errors       → Explicit try/catch, no silent fails   │
│  3. Document trade-offs     → Alternatives considered, why chosen   │
│  4. Use failure protocols   → BLOCKED/CLARIFICATION_NEEDED if stuck │
│  5. Fix every surfaced gate error → Lint/type/test failures must    │
│     be fixed even on pre-existing code. "Pre-existing, unrelated"   │
│     is NOT a justification for skipping a failing quality gate.     │
├─────────────────────────────────────────────────────────────────────┤
│  REQUIRED: Use Edit/Write tools to apply code directly              │
│  NEVER: Modify outside {{allowed_scope}} | Skip error handling      │
│         Log sensitive data | Use deprecated APIs | Silent failures  │
├─────────────────────────────────────────────────────────────────────┤
│  OUTPUT: AAG Contract → Approach → Code → Trade-offs → Testing      │
│  CODE APPLICATION: Apply immediately with Edit/Write tools          │
│  VALIDATION: Monitor will test written code and provide feedback    │
└─────────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 844 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 844 lines · 11 tokens per session scan A 4da92d8b1fa5

Subscribe to this mod's changes

actor is an agent published in the GitHub repository azalio/map-framework (153 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 6,984 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

deep-paper-researcher

Token-isolated deep research agent for academic papers. Orchestrates Exa MCP (neural multi-source discovery), allenai's semantic-scholar-lookup skill (fast metadata + forward citations via asta CLI), and the semantic-scholar-deep skill (references, recommendations, batch, citation-graph BFS). Use when the user asks…

CodeAlive-AI/ai-driven-development · 210 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

developer

Implementer — writes production code, tests, and migrations. The "generic engineer" fallback when no narrower specialist exists. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 51 tokens

orchestrator

Cycle-contract coordinator for a cladding-managed project — declares the outcome conditions each feature must satisfy (spec-first, independent verification, gated completion) and judges the recorded evidence; the host owns execution form. Activate only when the connected project contains spec.yaml or the user…

qwerfunch/cladding · 69 tokens

planner

SSoT custodian — keeps spec.yaml structurally clean. Adds features, archives them, and ensures EARS pattern compliance. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 53 tokens

observability

Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can act on. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 61 tokens