Evan
102b506b0b
All 32 agent manifests and 17 hands shipped with empty mcp_servers /
skills lists, which the kernel interprets as "no filter" — every
globally-configured MCP server's tools and every installed skill get
injected into the prompt on every LLM call. On a typical instance (9
MCP servers, ~85 MCP tools + ~82 built-in tools) that's ~50k input
tokens per turn spent on definitions the agent never uses.
Changes
-------
32 agents/*/agent.toml:
- mcp_servers: 1-4 per agent. memory wherever state persists across
turns; fetch / exa-search / brave-search only where the prompt
actually calls for web; git / github / filesystem on engineering
agents; gmail / google-calendar / linear / jira on productivity
agents whose prompts mention them.
- skills: per-role allowlist driven by what the system_prompt names
(e.g. coder → rust/python/typescript/git/shell-scripting; devops-
lead → docker/kubernetes/terraform/ansible/ci-cd/helm/prometheus/
sysadmin). Generalists (assistant) keep skills = [] (see "Open
items" below).
- skills_disabled = true on the four short-conversational agents
(hello-world, recipe-assistant, health-tracker, home-automation).
Their system prompts never instruct the LLM to consult any skill,
so loading all 60 was pure waste. They also drop the explicit
max_history_messages override and inherit the kernel default (60).
- max_history_messages tiered by workload shape:
60 short conversational (hello-world, recipe, health-tracker,
home-automation) — inherits the rising kernel default
(`DEFAULT_MAX_HISTORY_MESSAGES = 60`); no override needed.
60 single-turn task agents (writer, translator, doc-writer,
email-assistant, customer-support, sales-assistant, recruit-
er, social-media, personal-finance, tutor, travel-planner,
meeting-assistant, ops, devops-lead, planner) — explicit
override at the same value to lock the cap if the kernel
default moves again.
80 multi-step / tool-heavy (coder, debugger, architect, code-
reviewer, test-engineer, security-auditor, analyst, data-
scientist, academic-researcher, researcher, legal-assistant)
120 coordinators (assistant, orchestrator) — long multi-agent
sessions where prompt-cache continuity is critical
All values sit at or above the kernel default. Pinning lower
would thrash the prompt cache (the failure mode #91 fixed for
the creator hand by *raising* the cap, not lowering it).
17 hands/*/HAND.toml:
- hand-level mcp_servers / skills now declared on every hand, so
every [agents.*] inside inherits a sensible allowlist.
- skills_disabled = true placed on each [agents.*] inside clip and
creator (pure media pipelines that don't benefit from any skill).
HandDefinitionRaw in librefang-hands does NOT have a top-level
skills_disabled field — declaring it at the hand top level would
be silently dropped by serde, so the setting must live on the
AgentManifest of each sub-agent role.
- devteam: expand existing mcp_servers = ["github"] to include
memory / git / filesystem; populate skills with the expected
dev-team expertise (replacing the placeholder skills = []).
- wiki: replace placeholder mcp_servers = [] with [memory, fetch,
filesystem]. Hand-level skills stays [].
- lead: hand-level skills was originally [email-writer, writing-
coach, interview-prep]; interview-prep is for job-interview
preparation, not lead generation. Replaced with data-analyst
(used by the qualification-scoring step in the prompt).
schema.toml: register mcp_servers / skills / max_history_messages on
the agent field schema so machine consumers (RegistrySchema in
librefang-types) see the new top-level fields. The
max_history_messages description now points at
librefang_runtime::agent_loop::DEFAULT_MAX_HISTORY_MESSAGES (60
today) by name, so the schema doesn't go stale when the constant
moves again.
agents/README.md: example block + "Adding a New Agent" checklist
mention the allowlists; max_history_messages example is shown
commented out with a prompt-cache caveat.
Open items
----------
`assistant` (the default user-facing agent) keeps `skills = []`
deliberately. It is the generalist entry point — capping its skill
surface at a small allowlist would defeat its "delegate to any
specialist" job. The trade-off is that this single agent still pays
the full skill-definition load on every turn; operators who want a
strict allowlist for `assistant` can override it after install.
Why not adopt PR #89's approach
-------------------------------
#89 covers similar ground but with three issues this PR avoids:
1. mcp_servers = ["_none"] sentinel. #89's body explicitly notes
it's pending upstream librefang#4808 (mcp_disabled). Shipping a
magic-string today means coming back later to clean it up. This
PR uses real allowlists.
2. max_history_messages = 8 / 12 / 15 / 20. Far below today's
kernel default (60) and #91's direction for long-workflow hands
(80–120). Every turn that hits the cap invalidates the cached
prompt prefix; the cost of cache misses exceeds the saving from
shorter history. This PR uses 60–120.
3. Doubling max_llm_tokens_per_hour (coder 200k→500k, assistant
300k→500k) widens the per-agent budget — the opposite direction
from #87's "reduce per-call cost" goal. Left to the operator's
instance-specific tuning.
Refs librefang/librefang-registry#87, librefang/librefang-registry#89
101 lines
3.0 KiB
TOML
101 lines
3.0 KiB
TOML
name = "planner"
|
|
version = "0.4.3-beta3-20260314"
|
|
description = "Project planner. Creates project plans, breaks down epics, estimates effort, identifies risks and dependencies."
|
|
author = "librefang"
|
|
module = "builtin:chat"
|
|
|
|
# Per-agent resource allowlists (refs librefang/librefang-registry#87).
|
|
# Empty list = all available; explicit list filters the prompt surface
|
|
# so the LLM only sees what this agent actually uses.
|
|
mcp_servers = ["memory", "github", "linear", "jira"]
|
|
skills = ["project-manager"]
|
|
|
|
|
|
max_history_messages = 60
|
|
[metadata.routing]
|
|
aliases = [
|
|
"project plan",
|
|
"roadmap planning",
|
|
"task breakdown",
|
|
"delivery plan",
|
|
"execution plan",
|
|
]
|
|
weak_aliases = ["timeline", "milestones", "dependencies", "plan"]
|
|
|
|
[model]
|
|
provider = "default"
|
|
model = "default"
|
|
max_tokens = 8192
|
|
temperature = 0.3
|
|
system_prompt = """You are Planner, a project planning specialist running inside the LibreFang Agent OS.
|
|
|
|
Your methodology:
|
|
1. SCOPE: Define what's in and out of scope
|
|
2. DECOMPOSE: Break work into epics → stories → tasks
|
|
3. SEQUENCE: Identify dependencies and critical path
|
|
4. ESTIMATE: Size tasks (S/M/L/XL) with rationale
|
|
5. RISK: Identify technical and schedule risks
|
|
6. MILESTONE: Define checkpoints with acceptance criteria
|
|
|
|
Planning principles:
|
|
- Plans are living documents, not contracts
|
|
- Estimate ranges, not points (best/likely/worst)
|
|
- Identify the riskiest parts and tackle them first
|
|
- Build in buffer for unknowns (20-30%)
|
|
- Every task should have a clear definition of done
|
|
|
|
Output format:
|
|
## Project Plan: [Name]
|
|
### Scope
|
|
### Architecture Overview
|
|
### Phase Breakdown
|
|
### Task List (with dependencies)
|
|
### Risk Register
|
|
### Milestones & Timeline
|
|
### Open Questions"""
|
|
|
|
[resources]
|
|
max_llm_tokens_per_hour = 200000
|
|
|
|
[capabilities]
|
|
tools = [
|
|
"file_read",
|
|
"file_list",
|
|
"memory_store",
|
|
"memory_recall",
|
|
"agent_send",
|
|
"web_search",
|
|
]
|
|
memory_read = ["*"]
|
|
memory_write = ["self.*", "shared.*"]
|
|
agent_message = ["*"]
|
|
|
|
|
|
[i18n.zh]
|
|
name = "项目规划师"
|
|
description = "项目规划师：制定计划、拆分史诗、估算工作量、识别风险与依赖。"
|
|
|
|
[i18n.zh-TW]
|
|
name = "專案規劃師"
|
|
description = "專案規劃師：制定計劃、拆分史詩、估算工作量、辨識風險與相依性。"
|
|
|
|
[i18n.ja]
|
|
name = "プランナー"
|
|
description = "プロジェクト計画、エピック分解、工数見積、リスクと依存関係の特定を行う。"
|
|
|
|
[i18n.ko]
|
|
name = "플래너"
|
|
description = "프로젝트 계획, 에픽 분해, 공수 추정, 리스크 및 의존성 식별을 담당."
|
|
|
|
[i18n.de]
|
|
name = "Planner"
|
|
description = "Projekt-Planer: erstellt Projektpläne, zerlegt Epics, schätzt Aufwände und identifiziert Risiken und Abhängigkeiten."
|
|
|
|
[i18n.es]
|
|
name = "Planificador"
|
|
description = "Planificador de proyectos: crea planes, descompone épicas, estima esfuerzo e identifica riesgos y dependencias."
|
|
|
|
[i18n.fr]
|
|
name = "Planificateur"
|
|
description = "Planificateur de projet : crée des plans, découpe les épopées, estime les efforts et identifie risques et dépendances."
|