goal-add-minor
Skill0 starsChanged 4 months agoMITView on GitHub
Use when designer adds new scope mid-session ('let's also do X', 'add this too', 'one more thing'). Appends minor goal to active-goals.json so additions are written-not-chat-context-dependent. Survives compaction + chat deletion.
In this repository68 other files it gives its agents.
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- art-bibleSkill
- asset-specSkill
- brainstormingSkill
- bug-reportSkill
- bug-triageSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- dispatching-parallel-agentsSkill
- estimateSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- gate-checkSkill
- goal-checkSkill
- goal-setSkill
- godot-engineSkill
- helpSkill
- map-systemsSkill
- narrative-designerSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- qa-planSkill
- quick-designSkill
- red-flag-scanSkill
- regression-suiteSkill
- retrospectiveSkill
- review-all-gddsSkill
- safety-pushSkill
- scope-checkSkill
- security-auditSkill
- session-closeSkill
- setup-engineSkill
- sprint-planSkill
- startSkill
- story-doneSkill
- story-readinessSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- team-artSkill
- team-audioSkill
- team-combatSkill
- team-economySkill
- team-infraSkill
- team-levelSkill
- team-marketingSkill
- team-narrativeSkill
- team-polishSkill
- team-releaseSkill
- team-securitySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Write a minor goal addition to production/session-state/active-goals.json → minor_goals_added[].
- Very specific: line 31
After /goal-set is locked + designer wants to extend scope without unfreezing
- Distinctive: line 47
Verify primary_goal exists.
- Distinctive: line 51
Ask designer (or infer):
- Distinctive: line 53
If MAJOR: propose new session OR rescoping primary goal.
- Distinctive: line 88
Don't block; just surface.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Goal Add Minor — Append Mid-Session Goal Addition
🌱 ShiningPlague-authored. No upstream version exists. Part of the session-goal tracking system (
/goal-set+/goal-add-minor+/goal-check).
Write a minor goal addition to production/session-state/active-goals.json → minor_goals_added[]. Prevents the scope-creep-in-chat-context failure mode where the assistant adds items verbally but they're never persisted.
If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.
When to fire
- Designer says: "also do X", "let's add Y", "one more thing", "while we're at it Z"
- The assistant notices an item being added to scope verbally without being written
- After
/goal-setis locked + designer wants to extend scope without unfreezing
When NOT to fire
- Primary goal not yet set (fire
/goal-setfirst) - The "addition" is actually a clarification of existing goal (no scope change)
- The addition is so big it should be a NEW session goal (suggest /goal-set in new chat)
Procedure
Step 1: Read active-goals.json
cat production/session-state/active-goals.jsonVerify primary_goal exists. If not, refuse — primary must be set first.
Step 2: Validate addition
Ask designer (or infer):
- Is this a MINOR add (small, fits within session scope) or MAJOR (should be its own goal/session)?
- If MAJOR: propose new session OR rescoping primary goal.
- If MINOR: continue.
Step 3: Append entry
Add to minor_goals_added[]:
{
"id": "MG-N", // auto-increment
"added_at": "YYYY-MM-DD",
"text": "<one sentence>",
"outcome": "PENDING"
}Update audit_log:
{
"ts": "YYYY-MM-DDTHH:MM:SSZ",
"event": "minor_goal_added",
"note": "<id>: <text>"
}Step 4: Surface to designer
Echo back:
- "Minor goal MG-N added:
<text>" - Current count: "Primary + N minors"
- Reminder: "All will be checked at session close via /goal-check"
Step 5: Auto-warn if scope creep
If minor_goals_added.length > 5:
- Warn: "Scope creep risk — N minor goals already added to session. Consider splitting into new chat OR formalizing as new session goal."
- Don't block; just surface.
Cross-skill awareness
- Triggered by hook keyword detection ("also do", "add this", "let's also") — surface propose, not auto-fire
/goal-checkreads minor_goals at session close- Defer-handoff format (Item 15b): if minor goal can't ship, structured handoff to active.md
Failure modes
- ❌ Adding without writing — defeats persistence purpose. Use this skill, don't just remember.
- ❌ Adding major scope as "minor" — push back, propose new session
- ❌ Skipping audit_log entry — breaks traceability
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.

