lanes-momentum-framework
Skill0 starsChanged 5 months agoMITView on GitHub
Turn an agency objective into a small, owned, reviewable lane board with a three-week horizon and daily momentum checks.
In this repository83 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- shep/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- shep/CLAUDE.mdCLAUDE.md
- advisory-version-checkSkill
- aeo-llm-content-plannerSkill
- agency-command-centerSkill
- agency-morning-briefSkill
- agency-scorecardSkill
- agent-runbookSkill
- agent-usageSkill
- autonomy-budgetSkill
- backlink-pr-angle-generatorSkill
- brand-kit-from-urlSkill
- browser-automationSkill
- building-autonomous-agentsSkill
- capability-mapSkill
- case-study-engineSkill
- clickup-apiSkill
- client-dashboardSkill
- client-health-scoreSkill
- client-onboarding-osSkill
- cli-llm-routingSkill
- codebase-mapSkill
- command-from-your-phoneSkill
- competitor-content-gap-analysisSkill
- connection-monitorSkill
- content-brief-generatorSkill
- determinism-patternSkill
- dispatch-and-briefSkill
- division-operating-modelSkill
- dreamingSkill
- durable-stateSkill
- entity-topical-authority-mapperSkill
- first-real-jobSkill
- founding-circle-ai-securitySkill
- gbp-competitor-auditSkill
- goal-modeSkill
- host-your-agentSkill
- html-reportsSkill
- instinct-bridgeSkill
- evolveSkill
- learn-evalSkill
- learnSkill
- promoteSkill
- skill-createSkill
- internal-linking-auditorSkill
- keyword-deep-diveSkill
- ladder-auditSkill
- launch-websiteSkill
- llm-citation-auditSkill
- migration-seo-paritySkill
- migration-visual-checkSkill
- model-gear-routerSkill
- multi-account-gatewaySkill
- multi-model-councilSkill
- night-shiftSkill
- novaSkill
- per-client-memory-routerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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 41
Run the daily lane walk: refine, unblock, narrow, defer, stop, or recommit.
- Distinctive: line 50
Do not fill the distant horizon with false precision.
- Distinctive: line 62
Do not mark a card green until the definition of done is evidenced.
- Distinctive: line 75
Expected output: Keep the founder as commander.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lanes Momentum Framework
Purpose
Convert a messy set of ideas, tasks, and fire drills into a small operating board that makes the next three weeks visible. The framework is for commanders: the person who chooses the outcome, assigns one accountable owner, gives the team enough context to act, and spends attention on judgment rather than serial execution.
Inputs
- Organization or team name.
- Desired outcome or quarter.
- Candidate work and known constraints.
- People who can own meaningful outcomes.
- Evidence sources and current dashboards.
Processing
- Brain-dump candidate work without pretending the first list is the plan.
- Group work into meaningful outcomes; keep tasks inside cards, not as lanes.
- Choose the top three or four active lanes.
- Assign exactly one accountable owner per lane.
- Plan Week 1 in detail; keep Weeks 2–3 lighter and hold the rest in Beyond.
- Link each lane to a mission brief with context, definition of done, source, and review gate.
- Run the daily lane walk: refine, unblock, narrow, defer, stop, or recommit.
- Move completed cards to the done shelf and use the evidence to reset priorities.
Board rules
- White = not started; yellow = in work; red = blocked; green = done and moved to the shelf.
- A lane is a meaningful project/outcome, not a diary, task dump, or artifact wall.
- One owner per lane. Supporters may contribute; they do not dilute accountability.
- The commander should not own every lane. Preserve energy for prioritization, context, and the final 10%.
- Do not fill the distant horizon with false precision.
- Daily alignment beats a weekly meeting that discovers drift too late.
Outputs
- A completed board using
templates/lanes-board-template.md. - One mission brief per active lane using
templates/mission-brief-template.md. - A daily lane-walk decision log.
- A done shelf with evidence links.
Review gate
Do not mark a card green until the definition of done is evidenced. Treat external writes, publishing, billing, permissions, and client-facing actions as separate approvals in the linked mission brief.
Examples
Example 1 — agency fulfillment
Input: SEO delivery, web implementation, AI experiments, sales, and reporting are all competing for attention.
Expected output: Fulfillment becomes the first lane; service implementation cards are assigned to one owner; AI experiments move to Beyond until the delivery bottleneck is reduced.
Why correct: The board reflects the constraint and protects the highest-leverage outcome.
Example 2 — overloaded commander
Input: The founder is listed as owner of every lane.
Expected output: Keep the founder as commander; assign each meaningful lane to the strongest available candidate and use a brief plus daily walk to coach them.
Why correct: Ownership creates a testable opportunity for the team to rise without making the commander the serial bottleneck.
Example 3 — blocked external action
Input: A dry run recommends publishing a press release, but no review has occurred.
Expected output: Mark the card review-gated; save the draft and evidence; do not publish.
Why correct: Analysis and external execution are distinct stages.
Evidence source
Distilled from the AMM mastermind session transcript, especially segments 244–406, 407–561, and 667–775. The session’s reusable governing document is docs/operating-model/lanes-momentum-framework.md.
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.

