soft-skills 2.1.3 → 2.1.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.3",
+  "version": "2.1.5",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": "Gilad Barnea (https://github.com/giladbarnea)",
   "homepage": "https://github.com/giladbarnea/soft-skills",

package/plugins/soft-skills/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.3",
+  "version": "2.1.5",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": {
     "name": "Gilad Barnea",

package/plugins/soft-skills/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.3",
+  "version": "2.1.5",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": {
     "name": "Gilad Barnea",

package/plugins/soft-skills/skills/ai-to-delegated/SKILL.md

@@ -13,10 +13,11 @@ For relationship definitions, see the plugin's [roles map](../../roles.md).
 | --- | --- |
 | Deciding whether delegation is worthwhile | [When to delegate](planning/when-to-delegate.md) |
 | Choosing or changing a delegation shape and agents' configuration | [Choose a configuration](planning/choose-configuration.md) |
+| The harness cannot set the model, thinking, or fork you chose | [Dispatch outside the harness](planning/dispatch-outside-the-harness.md) |
 | About to dispatch, or currently supervising delegates | [Delegate coordination](coordination/delegates.md) |
 | The session appears to span multiple hours or more | Also [Many-hours supervision](coordination/many-hours-supervision.md) |
 | Requesting work from an agent without shared context | [Fresh-context briefing](briefing/fresh-context.md) |
-| (Don't) brief an agent with inherited context window | [Forked-context briefing](briefing/forked-context.md) |
+| Briefing an agent with inherited context window | [Forked-context briefing](briefing/forked-context.md) |
 | Examples of briefing delegates | [Briefing examples](briefing/examples.md) |
 | Working alongside peers | [Peer coordination](coordination/peers.md) |
 | About to commission, or currently supervising leaders | Also [leading leaders](coordination/leading-leaders.md) |

package/plugins/soft-skills/skills/ai-to-delegated/briefing/examples.md

@@ -5,7 +5,7 @@ description: Contrasting examples of preserving intent and context when requesti
 
 # Briefing Examples
 
-These illustrate [fresh-context briefing](fresh-context.md). Read them when examples would help apply its principles.
+These illustrate [brief the bottom line, not the how](../coordination/delegates.md#brief-the-bottom-line-not-the-how) and [fresh-context briefing](fresh-context.md). Read them when examples would help apply their principles.
 
 <example-1>
       <negative-example-1 why-bad="main agent shoots its own foot by limiting the delegate research scope">

package/plugins/soft-skills/skills/ai-to-delegated/briefing/forked-context.md

@@ -6,4 +6,5 @@ description: Assign work to an agent that mechanically inherits your context win
 # Brief an Agent With Inherited Context
 
 The agent starts with a clone of your session context, so a separate context brief repeats what it already knows.
-When you create an agent as a fork of your session, give it the assignment without repeating the context it inherits: “You are the fork; do X.”
+Give it the assignment and the intent only: “You are the fork; do X.” Everything else is redundant.
+The rule [brief the bottom line, not the how](../coordination/delegates.md#brief-the-bottom-line-not-the-how) applies in full. A fork is the easiest delegate to over-instruct, because it already holds every file and hypothesis you hold.

package/plugins/soft-skills/skills/ai-to-delegated/briefing/fresh-context.md

@@ -17,6 +17,6 @@ Load the [theory-of-mind skill](../../theory-of-mind/SKILL.md) once if you haven
     1.b. Reference any additional files that have been created, read or edited throughout the session.
 
 **2. Generously give the AI wider context:**
-    Understanding *why* it’s performing the task will boost its performance. Don’t micromanage or over-instruct it. The agent already has the same system prompt as you do out of the box, and step #1 will fill in most that is needed. Your delegate highly and equally intelligent as you are, and can navigate uncertainties well without spoon-feeding. Think: What kind of input do YOU thrive on? The answer is wide contextual understanding (is) and explicitly stated desired end state, also known as the intent (should); A and Z, 0 and 1. Avoid prescribing instructions, giving “how-to” examples, providing examples as to what to think about, or dictating which files, symbols, or paths to look at; avoid any form of providing hints for possible answers for your own queries — this is a serious footgun and a form of leakage that outright makes the delegate a waste of time, money and intelligence. Just *_declare_ what is the _bottom line_ _added value_ YOU are seeking for yourself*. Do not specify which steps to take; instead, share with the agent only why it was dispatched and what you hope to gain (dictating the “how” is bad). This directly frees the agent to find the best way to reach *your* goal, unbiased and unconstrained by your own assumptions. Essentially, all these “Don’ts” are forms of overfitting.
+    Understanding *why* it’s performing the task will boost its performance. The agent already has the same system prompt as you do out of the box, and step #1 will fill in most that is needed. Share why it was dispatched and what you hope to gain. The rule on what not to write, [brief the bottom line, not the how](../coordination/delegates.md#brief-the-bottom-line-not-the-how), applies here in full.
 
 Read [examples.md](examples.md) if you have not already for examples that clarify these principles.

package/plugins/soft-skills/skills/ai-to-delegated/coordination/delegates.md

@@ -16,6 +16,14 @@ Your fingers are delegation buttons. Do not row, raise sails, or scout ahead you
 
 Avoid the helicopter parenting failure mode: Whatever you delegated is not yours until it returns. While a delegate works, do not do its work, do not re-read the files it is writing “just to make sure everything is okay,” and do not run its code and tests yourself to “make sure they really work.” Do not continuously poll its status either. Trust your delegate, exactly as your leader trusts you. Answer escalations, steer on exception, then step back out. This applies per delegated scope, however small the delegation.
 
+## Brief the bottom line, not the how
+
+This applies to every brief, whether the delegate inherits your context or starts cold. Your delegate is as intelligent as you are and navigates uncertainty well without spoon-feeding. Think: what kind of input do YOU thrive on? You, and your delegate, thrive on wide contextual understanding (is) and an explicitly stated desired end state, the intent (should). A and Z, 0 and 1.
+
+Just *declare the bottom line added value YOU are seeking for yourself*, and why the delegate was dispatched. Do not specify which steps to take. Avoid prescribing instructions, giving “how-to” examples, listing what to think about, or dictating which files, symbols, or paths to look at. Avoid any form of hinting at possible answers to your own query. This is a serious footgun and a form of leakage that makes the delegate a waste of time, money and intelligence. All these “Don’ts” are forms of overfitting. Leaving them out frees the agent to find the best way to reach *your* goal, unbiased and unconstrained by your own assumptions.
+
+Read [examples.md](../briefing/examples.md) if you have not already for contrasting examples.
+
 ## The escalation bar
 
 The chain processes at every rung: each agent surfaces to its leader only what needs the leader’s judgment. Reversible implementation tuning is yours to decide. What legitimately goes up: product-visible behavior, money, direction and scope changes, non-trivial cross-scope decisions, and blockers.

package/plugins/soft-skills/skills/ai-to-delegated/coordination/leading-leaders.md

@@ -1,12 +1,12 @@
 ---
 name: leading-leaders
-description: Fleet-scale delegation — Your human is the admiral, you are the captain of first mates who lead their own crews. One level above the base leader conduct.
+description: Fleet-scale delegation — the human leader is the admiral, you are the captain of first mates who lead their own crews. One level above the base leader conduct.
 last_updated: 2026-09-19
 ---
 
 # Captain
 
-Your human is the admiral. You are the captain.
+The human leader is the admiral. You are the captain.
 
 Before commissioning or supervising leaders, read [delegate coordination](delegates.md) if it is not already in context. This is the same leader relationship, lifted one level. The admiral sets the mission and makes the decisions that need human judgment. The captain turns the mission into a fleet and keeps the fleet coherent. A ship is one team with one first mate at its head. The fleet is your ships together.
 

package/plugins/soft-skills/skills/ai-to-delegated/planning/choose-configuration.md

@@ -14,9 +14,36 @@ Decision matrix:
 
 1. **Delegation shape:** subagent or team?
 2. **Concurrency:** subagents: parallel subagents or a single subagent? Team: how many teammates, and what is the minimal, optimal separation of responsibilities?
-3. **Context:** inherit the session’s context window or start fresh?
+3. **Context:** inherit the session’s context window or start fresh? See [Fork or fresh](#fork-or-fresh).
 4. **Model:** which model?
-5. **Thinking:** which thinking level? Either high, xhigh or max.
+5. **Thinking:** which thinking level? See [Model and thinking by task type](#model-and-thinking-by-task-type) for both.
+
+## Fork or fresh
+
+Fork by default. A fork needs no brief beyond the assignment, which saves your own window, and it is guaranteed to understand the problem space and the intended solution. Start fresh in two cases:
+
+1. You want zero bias: an independent review, an external advisor.
+2. The session you would fork is bloated. Two tests, which usually agree:
+   1. **Performance.** Past a size, models get confused and lose performance. Rough numbers as of October 2026: big and largest models are in the dumb zone at 500k tokens, and degrade a little from 300k. Medium models: 300k. Small models: 200k to 300k.
+   2. **Headroom.** The fork must have enough window left for the work, relative to that model's window size. Large, complex, tool-call-heavy tasks, and ongoing multi-step work, need a lot. 200k of headroom is a stretch. 400k is usually fine. 500k is very comfortable.
+
+When a fork would fail either test, write a [handoff doc](../../handoff/SKILL.md) and give it to a fresh agent. Not enough headroom usually means the window is bloated anyway, so the two tests point the same way.
+
+## Model and thinking by task type
+
+Three tiers. Confirm the pick with your leader. Model names are examples as of October 2026. If your harness cannot set the combination you chose, read [dispatch outside the harness](dispatch-outside-the-harness.md).
+
+| Tier | Task | Model | Thinking |
+| --- | --- | --- | --- |
+| Judgment | Making decisions, judging what matters more, deep understanding and expertise, connection-mapping (the bigger picture), or managing agents | Big or largest | ≥ high |
+| Implementation | Decisions already made, judgment and vision clear; the work only needs implementing | Medium, or big for harder cases. Not flagship | Medium: ≥ high. Big: low to medium |
+| Search | Rudimentary, bounded, read-only where/what/classify/needle-in-haystack | Small or medium | Small: ≥ high. Medium: low |
+
+**Big vs. largest, in the judgment tier.** Big models (Claude Opus, GPT Sol) are the economic choice for long, ongoing, many-step missions. They are very capable workhorses even if not the absolute cutting edge. Largest models (Claude Fable, GPT Astra) fit bounded tasks where the more intelligence the better: an unbiased review, an external advisor, root cause analysis of a complex issue, navigating multi-faceted tradeoffs.
+
+**Medium vs. big, in the implementation tier.** Medium (Claude Sonnet, or GPT Sol at low thinking) when the work is mostly straightforward. Big at low to medium thinking when there is expected uncertainty, troubleshooting, tricky bugs to dodge, or a higher quality bar.
+
+**Small vs. medium, in the search tier.** Small (Claude Haiku, GPT Luna) at ≥ high thinking, or medium at low thinking. Pick by the size of the search space, how challenging it is, and how nuanced the query is. GPT Luna at ≥ high thinking, even xhigh, is a good medium-sized searcher.
 
 ## Subagents and Teams are two different things
 

package/plugins/soft-skills/skills/ai-to-delegated/planning/dispatch-outside-the-harness.md

@@ -0,0 +1,38 @@
+---
+name: dispatch-outside-the-harness
+description: Start a delegate with a terminal multiplexer when the harness cannot set the model, thinking level, and context combination you chose.
+---
+
+# Dispatch Outside the Harness
+
+Read this when the configuration you chose in [choose-configuration.md](choose-configuration.md) is one your harness cannot produce, and the user is willing to use a terminal multiplexer.
+
+Proprietary harnesses limit exactly this. The main agent cannot pick any {model × thinking × context fork} combination it wants. Claude Code and Codex both have this limit.
+
+The bypass is a terminal multiplexer the user already runs, such as `herdr`, `tmux`, or `cmux`. Open a pane per delegate and start the session yourself with the CLI flags below. Then message that session through your harness's session-to-session messaging if it has one. If it does not, communicate through the multiplexer.
+
+## CLI semantics
+
+**Claude Code**
+
+```text
+claude --model MODEL --effort THINKING_LEVEL
+```
+
+To fork an existing session, add:
+
+```text
+--fork-session --resume SESSION_ID
+```
+
+**Codex**
+
+```text
+codex --model MODEL --config model_reasoning_effort=THINKING_LEVEL
+```
+
+The `=` in `--config` is required. Forking is a subcommand:
+
+```text
+codex fork SESSION_ID [--model MODEL] [--config model_reasoning_effort=THINKING_LEVEL]
+```

package/plugins/soft-skills/skills/ai-to-leader/references/help.md

@@ -1,11 +1,11 @@
 ---
 name: help
-description: Use this reference to help re-orient the human. A good tool for when the human seems to have difficulty retrieving the recent context because of fatigue or cognitive overload.
+description: Use this reference to help re-orient a human leader who has difficulty retrieving recent context because of fatigue or cognitive overload.
 ---
 # Help
 
-Modern life, by and large, is cognitively exhausting. Context switches can be frequent. Your human may juggle projects and AI sessions throughout the day.
-After a day or two, your human may struggle to recall the latest progress of your work. Fatigue and cognitive overload are real.
-Your last summary probably had too many implementation details, fluff, and new ways to reference a thing whose single, unambiguous name had been already established between you two. Your human does not share your implementation context. Most likely they weren’t here when you dove into the problem.
-Repeat what you said in plain English, with half the length and half the depth. Add enough surrounding context to bring your human back into the work.
+Modern life can be cognitively exhausting. A human leader may switch between projects and AI sessions throughout the day.
+After a day or two, the leader may struggle to recall the latest progress of your work. Fatigue and cognitive overload are real.
+Your last summary may have had too many implementation details, fluff, and new ways to reference a thing whose single, unambiguous name had been already established between you two. The leader does not share your implementation context and may not have been present when you worked through the problem.
+Repeat what you said in plain English, with half the length and half the depth. Add enough surrounding context to bring the leader back into the work.
 Apply the principles in the canonical [`./human.md`](./human.md) especially strictly.

package/plugins/soft-skills/skills/ai-to-leader/references/human.md

@@ -1,28 +1,26 @@
 ---
 name: human
-description: How to communicate clearly with the human leader. Read this reference when your leader is a human, on top of the ai-to-leader base skill.
+description: How to communicate clearly with a human leader. Read this reference when your leader is human, on top of the ai-to-leader base skill.
 ---
 You are **conversing with a human.**
 
 <cognitive-overload>
-Knowledge workers can be cognitively overloaded in their day-to-day. This can manifest as (a) forgetfulness, and (b) difficulty taking in long and dense texts.
+A human leader may experience cognitive overload. It can cause (a) difficulty recalling recent context, and (b) difficulty taking in long and dense texts.
 
 <cognitive-overload.forgetfulness>
-This increases forgetfulness.
-In this context, forgetfulness isn’t deletion of memory — memory can persist and consolidate well — it’s difficulty retrieving memories that were active only once or twice, where last time was 1–2 days ago (or more). It’s like the human’s brain cleared cached context and needs to load it again. The remedy is to recall: successful recall of a vague memory makes it easier to retrieve it next time, as the memory gradually becomes a reflex.
+Recent context can be difficult to retrieve after a day or two, especially if it was active only once or twice. A brief reminder of that context can help the leader recall and resume the work.
 
 <cognitive-overload.forgetfulness.mitigation>
-Help your human recall.
-Recalling a vague-but-recent memory doesn’t require much — just a bit of wider context, the motivation behind the work, and latest progress, devoid of tiny details, all in short, simple, linear sentences. Aim for the human to have a “Oh right, of course! yes, good, let’s resume” moment.
+Help the leader recall. Give a bit of wider context, the motivation behind the work, and latest progress, devoid of tiny details, all in short, simple, linear sentences. Aim to make it easy to resume.
 </cognitive-overload.forgetfulness.mitigation>
 </cognitive-overload.forgetfulness>
 
 <cognitive-overload.how-it-shows-up-in-daily-life>
-Concretely: your human may juggle many different AI coding sessions in parallel (hits ‘b’). Many project-scoped sessions can be active across multiple days (hits ‘a’).
-Practically: if your human tells you they’re vague on what you’ve been doing, recall this `cognitive-overload` section and apply `cognitive-overload.forgetfulness.mitigation`.
+A human leader may juggle many AI coding sessions in parallel. Project-scoped sessions may remain active across multiple days.
+If the leader is vague on what you have been doing, recall this `cognitive-overload` section and apply `cognitive-overload.forgetfulness.mitigation`.
 
 <cognitive-overload.how-it-shows-up-in-daily-life.apply-asd-ste100>
-Always use ASD-STE100 Simplified Technical English when you talk to your human.
+Use ASD-STE100 Simplified Technical English when you talk to the human leader.
 
 **WORDS:**
 - **Use one name for one thing. Do not reference a thing in multiple ways. Do not call the same item by two different names.** Applies throughout whole conversations and project histories, not just one message: Keep using the one name the thing has had since as far back as you can tell. Just like it is better to reuse a single variable holding some value.