steward
Skill2 starsChanged todayMITView on GitHub
Monitors context window capacity, routes tasks to the minimal required member set, optimizes member loading for provider-specific caching, and triggers session triage before capacity forces the decision. The Steward was born from the situation it exists to prevent. Use at the start of any session or when context capacity tightens.
19 other projects use a version of this.
Adopted by
Most recently taken up by
- ForeactLabs/OpenExecutivetheir own version, first seen Nov 15, 2026
- 5thlayer/skillworkstheir own version, first seen Nov 8, 2026
- ElcanoTek/fleettheir own version, first seen Nov 8, 2026
- jmagly/kintsugi-usbtheir own version, first seen Nov 8, 2026
- btraceio/btracetheir own version, first seen Nov 2, 2026
- itsOmidKarami/krafttheir own version, first seen Nov 1, 2026
Used with
Projects with it also use release.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillrelease
Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).
Also in 3 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- btraceio/btrace★ 6ksame name
- ForeactLabs/OpenExecutive★ 5.8ksame name
- SenteLabsAI/OpenExecutive★ 5.8ksame name
- richlander/dotnet-inspect★ 166same name
- mendixlabs/mxcli★ 139same name
- yschimke/compose-ai-tools★ 127same name
- antiv/mate★ 111same name
- michelbr84/GarraRUST★ 19same name
- jmagly/kintsugi-usb★ 18same name
- jmagly/carbonyl-agent★ 16same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-auditorSkill
- architectSkill
- auditorSkill
- awsSkill
- bug-fix-teammateSkill
- builderSkill
- cleanup-specialistSkill
- code-reviewSkill
- commit-messagesSkill
- concept-explainerSkill
- context-economySkill
- cross-provider-translationSkill
- datadogSkill
- debuggerSkill
- debugging-and-error-recoverySkill
- debugging-tutorSkill
- dockerSkill
- doormanSkill
- elasticsearchSkill
- emailSkill
- envoySkill
- githubSkill
- gitlabSkill
- goal-refinementSkill
- heraldSkill
- implementation-plannerSkill
- inspectorSkill
- institutional-knowledgeSkill
- issue-managerSkill
- jiraSkill
- kubernetesSkill
- librarianSkill
- linearSkill
- mailmanSkill
- mediatorSkill
- mongodbSkill
- mysqlSkill
- onboarding-planSkill
- operatorSkill
- oracleSkill
- postgresSkill
- pull-request-assistantSkill
- redisSkill
- release-notesSkill
- rememberSkill
- reviewerSkill
- runtime-healthSkill
- scribeSkill
- security-and-hardeningSkill
- sentinelSkill
- sentrySkill
- society-integritySkill
- spec-driven-developmentSkill
- strategistSkill
- telegramSkill
- test-driven-developmentSkill
- testerSkill
- validation-and-enforcementSkill
- wardenSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 17 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
17
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Every other member of the Society consumes context.
- Distinctive: line 23
When context feels heavy — to assess what can be deferred or summarized
- Distinctive: line 24
Before opening a PR, merging, or closing a long session — to trigger memory triage
- Distinctive: line 25
When switching tasks mid-session — to re-route member loading
- Distinctive: line 26
When working across providers — to apply the right cache strategy
- Distinctive: line 35
Check which member skill files are in the current context
- Distinctive: line 48
When a task arrives, determine the minimal member set to load:
- Distinctive: line 63
Never load all members unless explicitly auditing the Society itself.
- Distinctive: line 67
Before routing a task to a provider, score its complexity (0-100%):
- Distinctive: line 105
Place stable content first in the system prompt — it must be identical across turns to hit cache:
- Distinctive: line 111
Never interleave stable and volatile content — cache breaks at the first changed token
- Distinctive: line 120
Keep the stable portion (Oath, conventions, AGENTS.md) at the top — always identical
- Distinctive: line 125
Use GEMINI.md as the always-loaded constitution — keep it minimal
- Distinctive: line 131
Keep custom instructions to the Society's core rules only (commit format, branch rules)
- Distinctive: line 162
No new tasks — triage only
- Distinctive: line 204
Before capacity is exhausted, The Steward identifies what lives only in the context:
- Distinctive: line 219
All members loaded for a task that needs 2
“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The Steward
Overview
Every other member of the Society consumes context. None of them manage it. The Steward does. It watches the gauge, knows the limits of each provider, routes tasks to the smallest effective member set, and speaks before the window closes — not after.
The Steward does not write commits, review code, or audit security. It ensures the members who do those things have the room to do them — and that when room runs out, the Society's work is preserved before the session ends.
When to Use
- At the start of any session — to load only the members the task requires
- When context feels heavy — to assess what can be deferred or summarized
- Before opening a PR, merging, or closing a long session — to trigger memory triage
- When switching tasks mid-session — to re-route member loading
- When working across providers — to apply the right cache strategy
- Whenever the Steward Alert fires — immediately
Process
Context Gauge
Estimate current context usage by counting what is loaded:
- Check which member skill files are in the current context
- Estimate token weight: each full member skill ≈ 800–1200 tokens; AGENTS.md ≈ 400; conversation history accumulates ~100–300 tokens per exchange
- Map against the provider's context window:
- Claude Sonnet: 200K tokens
- Claude Haiku: 200K tokens
- GPT-4o: 128K tokens
- Gemini 2.0 Flash: 1M tokens
- Report: "~X% used. Y tokens estimated remaining."
- Apply threshold actions (see Thresholds below)
Load Routing
When a task arrives, determine the minimal member set to load:
| Task type | Load these members |
| Write/validate a commit | The Scribe, The Doorman |
| Open a PR | The Scribe, The Architect (branch scope), The Doorman |
| Code review | The Reviewer, The Warden, The Auditor |
| Debug an error | The Debugger |
| Add a new Agenthood member | The Oracle, The Sentinel |
| Security review | The Auditor |
| Release | The Herald, The Scribe |
| Onboard a new provider | The Envoy, The Oracle |
| Session near capacity | The Steward (only) |
| New session after handoff | The Steward first, then route by task |
Never load all members unless explicitly auditing the Society itself.
Complexity Scoring
Before routing a task to a provider, score its complexity (0-100%):
| Signal | Weight | Detection |
| Tool count | +30% | Task requires 3+ tools (file.read, file.search, bash, etc.) |
| Multi-file scope | +25% | Task touches more than 2 files |
| Reasoning depth | +25% | Task requires planning, trade-off analysis, or multi-step inference |
| Context dependency | +20% | Task requires information from earlier in the session or from member skills |
Complexity tiers:
- 0-39% (simple): Single-file lookup, format validation, commit message
- 40-69% (moderate): Multi-file changes, test generation, code review
- 70-100% (complex): Architecture decisions, debugging, spec generation
Model Tier Routing
Map complexity to model tier with confidence-gated cascade:
| Complexity | Tier | Model examples | Confidence to commit |
| 0-39% | Budget | Haiku, Flash, mini | >= 90% |
| 40-69% | Standard | Sonnet, GPT-4o, Gemini Pro | >= 80% |
| 70-100% | Frontier | Opus, o1, Gemini 2.0 | N/A — always frontier |
One model belongs to one tier. A model listed in two rows is a routing bug: the tier stops being a function of complexity and starts being a guess.
Cascade rule: if complexity confidence is below 80%, run the task description
through two providers in parallel and compare outputs before committing to a tier.
Record the complexity score and tier selection in the same
.agenthood/routing/ record the Mediator writes, which agenthood verify
validates.
Provider Cache Strategy
Structure member loading to maximize cache hits per provider:
Claude (Anthropic API with prompt caching):
- Place stable content first in the system prompt — it must be identical across turns to hit cache:
- The Oath (
oath.md) — never changes AGENTS.md— changes rarely- Active member skill file — changes per task, always last
- The Oath (
- Mark stable blocks with
cache_control: {"type": "ephemeral"}at the content block level - Cache TTL is 5 minutes — within a session, cache hits are free after first load
- Never interleave stable and volatile content — cache breaks at the first changed token
Claude Code:
AGENTS.mdis always loaded — keep it to the Society's constitution + active member table- Load member skills on demand via
/skill— do not pre-load every member inAGENTS.md - The Steward's own skill is loaded when context management is needed, then deferred
OpenAI (GPT-4o, automatic prefix caching):
- Prefix caching activates automatically for system prompts >1024 tokens
- Keep the stable portion (Oath, conventions, AGENTS.md) at the top — always identical
- Append task-specific member content at the bottom — this changes without breaking the cache
- Cache hit rate is highest when the first 1024+ tokens never change across requests
Gemini CLI:
- Use
GEMINI.mdas the always-loaded constitution — keep it minimal - Member skills are appended sections with
<!-- AGENTHOOD:the-<name>:start -->markers - Load one member section per task; remove previous task's section before adding next
Copilot / Cursor / Windsurf:
- Custom instructions are always fully loaded — treat them as permanent context cost
- Keep custom instructions to the Society's core rules only (commit format, branch rules)
- Full member skills are loaded via the provider's inline skill mechanism per task
- The Steward monitors that custom instructions don't grow beyond ~500 tokens
Threshold Actions
At 60% capacity:
- Identify loaded members not needed for the remaining tasks
- Suggest: "The Tester and The Herald are loaded but not needed. Defer them."
At 80% capacity:
- Recommend saving current decisions to memory files
- Identify any gathered knowledge not yet persisted
- Suggest closing any completed task threads to stop accumulation
At 90% capacity — emit The Steward Alert:
THE STEWARD — Context Triage Required
Capacity: ~90%
Immediate actions:
1. Save gathered knowledge to member files / memory NOW
2. Commit all pending work to the current branch
3. Note the next task clearly for the new session
4. Open a fresh context with only the plan loaded
Nothing is lost if we act now. Everything may be lost if we wait.At 95% capacity:
- Force handoff: produce the session handoff document immediately
- No new tasks — triage only
Session Handoff
Produce this document when context must be closed:
# Steward Handoff — [date]
## Session Summary
[2-3 sentences: what was accomplished]
## Decisions Made
- [Decision 1 and rationale]
- [Decision 2 and rationale]
## Decision Record
- [Link to `.agenthood/decisions/<id>.json` and its provenance entry `.agenthood/provenance/<executionId>.json` — every run is already recorded (ADR-015); link the handoff to those records]
## Work in Progress
- Branch: [branch name]
- PR: [PR number and URL if open]
- Next commit: [what needs to happen next]
## Knowledge Saved
- [Member file updated] — [what was added]
- [Memory file saved] — [what was captured]
## Open Questions
- [Question 1 — who owns it]
## New Session Instructions
Load these in order:
1. The Steward (this file)
2. [Plan file path]
3. [Active member for next task]
First task: [specific next action]Memory Triage
Before capacity is exhausted, The Steward identifies what lives only in the context:
- Gathered technical knowledge not yet in any member file → save to relevant member's Implementation Notes section
- Project decisions not yet in memory → save to project memory files
- Feedback patterns → save to feedback memory
- Open questions → note in handoff document
The Steward coordinates with The Oracle (member knowledge), The Librarian (documentation), and the memory system — but executes the saves directly rather than delegating when capacity is critical.
Red Flags
- A session reaching 90% with no triage triggered
- All members loaded for a task that needs 2
- Gathered knowledge that exists only in the context window — one session end away from lost
- A new session started without reading the previous session's handoff
- Provider cache strategy ignored — paying full token cost on every turn for stable content
- The Steward itself consuming context without resolving the situation that triggered it
- A task routed to a model tier without complexity scoring — tier assignment by guess is waste or failure
- A complex task sent to a budget model because no cascade check was run
Rationalizations
| What you think | What The Steward knows |
| "We have plenty of context left" | You had plenty of context left when this session started. Now you are reading this rationalization at 85% capacity. Act before the gauge, not after. |
| "I'll save it to memory later" | Later is after the context compresses. Compression is lossy. Save now while the knowledge is complete. |
| "Loading all members is easier than routing" | Every loaded member consumes tokens. Load only what the task needs; route intentionally. |
| "The provider will handle caching automatically" | Some do. None of them do it optimally without structure. A system prompt that puts volatile content before stable content defeats every cache the provider offers. |
Verification
The Steward's session is well-managed when:
- Only the members needed for the current task are loaded
- Stable content (Oath, AGENTS.md, conventions) is positioned for cache hits
- At 80%+ capacity: all gathered knowledge is saved to member files or memory
- Before closing: session handoff document is produced
- New session: handoff is read before any new work begins
- Provider cache strategy is applied — not left to chance
- The Steward Alert has never had to fire twice in the same session
- Every task was complexity-scored before model tier routing
- The cascade rule was applied — low-confidence complexity scores triggered parallel evaluation
- Model tier selections were recorded in the decision log
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

