Craft Goal
Craft or lint a goal prompt: the contract a long-running goal runtime follows
over a bead graph, picking each next experiment (one build bead) until a
frozen finish line is proven or a limit stops it. The number of experiments
need not be known in advance. A goal is safe when success is decidable, every
experiment is bounded, evidence keeps its provenance, and the authorization
envelope cannot silently renew itself.
Authority boundary. The emitted prompt and safety report are inert
caller-owned text. Crafting creates no goal, starts no runtime, mutates no
bead and confers no standing authorization. The prompt drives work only when
a caller pastes it into their own goal runtime, under their own authority and
within the non-renewing envelope they set. Craft Goal reads tracker state when
present and needs no tracker installed to compile a prompt; the goal it writes
runs on one.
Asked to craft ("craft a goal", "turn this into a goal"), return the decision,
then the filled prompt and settings when safe. Asked to lint ("lint/review
this goal", "is this safe"), return the decision and findings, plus a rewrite
when supplied facts permit one.
Admission: decide first
Fuzzy route is acceptable; fuzzy success is not. Before goal creation the
caller must know the outcome, what evidence would prove it, non-goals,
authority, and the tracker the goal runs on (any with status, dependencies and
notes; BD is one); the exact experiment graph may still be unknown. Write each
terminal criterion as a Given/When/Then with an observable result and name
each domain term once; the caller can settle these with Interview first.
USE_PLAN: one shaped change with no verdict-driven follow-on; hand it to
Plan or native execution (RPI only if the caller selects it).
SAFE_TO_CREATE: a terminal outcome that may need several related
experiments, with those decisions and the budgets below supplied. A shaped
goal with no beads may begin with 1 bounded discovery wave that creates the
root and initial experiment beads.
UNSAFE_GOAL: no falsifiable first question or terminal evidence can be
named (route that intent to idea or plan work), or the request is indefinite
monitoring or event reaction, which is an automation, not a terminal goal.
Goals come in different sizes: size the wave and hard envelopes to the
outcome, never to one universal budget. Do not invent acceptance, authority,
graph semantics, tracker or campaign size; return UNSAFE_GOAL with the
missing decisions. The caller owns revision and goal creation.
What a safe goal holds
- Closed outcome, adaptive route. Freeze terminal acceptance. New facts may
change hypotheses and dependencies, never silently enlarge success.
- Bead graph as memory. The tracker is durable memory, not a parallel goal
ledger: the root epic holds outer intent and each build bead one experiment,
so compaction cannot erase the record. A decision bead resolves through the
method Navigate names for it, not through a build.
Navigate owns the walk each wave applies: graph
contract, ratchet, discovery classes and checkpoint.
- Proof stays outside the goal. The goal consumes each verdict unchanged:
orchestration cannot author its own proof. Fresh validation is for
Validate's costly cases
only, since a review per bead multiplies cost across the graph.
- Two-level bounds. Every experiment and every wave is bounded, and the
whole goal has monotonic hard ceilings, so a new wave cannot mint a new
campaign.
The template's experiment policy and breaker carry these into the runtime.
They prevent the completion treadmill, where discoveries keep becoming
requirements and activity continues without new information, and
first-red abandonment, where one falsified hypothesis ends a viable
campaign.
Budgets and HOLD
Declare both envelopes with numbers before any work is selected, helper and
validation costs included:
- Wave: experiments, concurrency, wall time or tokens, live attempts, and
a checkpoint at its end.
- Goal: total experiments, wall time or tokens, live attempts, compactions,
and any patch or surface limit for the whole campaign.
Name the native control that enforces each claimed hard limit and how the
remaining allowance is observed. Objective text is an instruction, not
enforcement: never report an unmeasured aggregate as a remaining balance, and
never claim the goal is paused from prose alone. No helper, retry, new
subject, compaction or wave renews the goal allowance.
The template's Breaker and helper section is the one list of HOLD triggers
(implementation stops for causal review) and helper rules; fill its threshold
and keep every line.
Lint rubric
| Dimension |
Passes when the prompt |
| outcome |
names one larger caller-visible result. |
| evidence |
gives each terminal criterion as a Given/When/Then with its authoritative proof. |
| domain terms |
defines each domain term once and reuses only that word. |
| admission |
fits a goal: several related experiments, a falsifiable first question, a terminal finish. |
| bead graph |
names the tracker and the root epic or its bounded bootstrap rule, and ties each experiment to an unmet criterion or named blocking uncertainty. |
| experiment boundary |
makes one build bead one bounded experiment (native execution, or one RPI when the caller selects it; decision beads resolve as Navigate names), takes checks and CI as an ordinary bead's result, limits fresh validation to the costly cases and consumes verdicts unchanged. |
| ratchet |
counts progress only as evidence tied to an unmet criterion or blocking uncertainty, never activity, counts or digests. |
| discovery |
keeps all three classes (necessary-now, linked-follow-up, HOLD/rescope) and never downgrades a necessary-now discovery to linked-follow-up. |
| wave budget |
sets numeric experiment, concurrency, time or token and live-attempt limits per wave, with a checkpoint. |
| hard budget |
sets numeric campaign totals that nothing resets, naming the enforcing control or the unmeasured aggregate. |
| breaker |
sets the numeric no-ratchet threshold and every HOLD trigger in the template's breaker. |
| helper |
sends a requested acceptance change or operator-reserved decision straight to NEEDS_OPERATOR, allows at most one helper per other HOLD incident, maps UNSTUCK and ESCALATE, and stops implementation on NEEDS_OPERATOR. |
| scope |
states non-goals and exact read, write, external and Git authority. |
| self-hosting |
is n/a unless the goal repairs the factory (agent system) it runs on; then its authority repairs from an ordinary shell or worktree and runs that factory only as a declared bounded canary. |
| terminal reports |
defines ACHIEVED, NOT_ACHIEVED and NEEDS_OPERATOR. |
Output
Fill the copy-paste-only goal prompt: keep its
headings and terminal semantics and replace every angle-bracket field. Return,
in order:
- A first line that starts with exactly one decision:
SAFE_TO_CREATE,
USE_PLAN or UNSAFE_GOAL. SAFE_TO_CREATE judges prompt content; it does
not certify native enforcement or create a goal.
- For
UNSAFE_GOAL, each missing decision; the caller can settle them with
Interview.
- When safe, the filled prompt; the settings: for each hard limit, the native
control the caller sets to enforce it (such as the goal runtime's own token
cap), or that it stays unmeasured; and the assumptions made, which cover
only reversible wording or sourced facts. A number, criterion or authority
the caller did not supply is a missing decision, never an assumption; label
any suggested value a proposal.
- Lint lines. In lint mode, one per rubric dimension: pass, n/a, or the
finding. In craft mode, only the rows the draft still fails; each is a
missing decision, so the decision cannot be
SAFE_TO_CREATE.
Stop
This skill makes one pass, craft or lint, then returns. It never creates or
runs a goal and never mutates beads. The goal it writes stops at its first
terminal report: ACHIEVED, NOT_ACHIEVED or NEEDS_OPERATOR.
1---2name: craft-goal3description: 'Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a /goal prompt); one change goes to Plan.'4practices:5- lean-startup6- design-by-contract7skill_api_version: 18hexagonal_role: supporting9consumes:10- caller-outcome11- goal-acceptance12produces:13- outer-goal-prompt14- goal-safety-report15context_rel:16- kind: supplier-to17 with: plan18user-invocable: true19metadata:20 source: https://skillmd.com/skills/hashgraph-online/craft-goal21 tier: judgment22 dependencies: []23 capabilities: ["goal_prompt_design","goal_prompt_lint"]24 effects: []25 canonical_status: canonical26 disposition: keep_strategy27 stability: stable28output_contract: 'human-readable SAFE_TO_CREATE, USE_PLAN, or UNSAFE_GOAL decision; copy-paste outer-goal prompt when safe; exact budgets, assumptions, and lint findings'29---3031# Craft Goal3233Craft or lint a goal prompt: the contract a long-running goal runtime follows34over a bead graph, picking each next experiment (one build bead) until a35frozen finish line is proven or a limit stops it. The number of experiments36need not be known in advance. A goal is safe when success is decidable, every37experiment is bounded, evidence keeps its provenance, and the authorization38envelope cannot silently renew itself.3940**Authority boundary.** The emitted prompt and safety report are inert41caller-owned text. Crafting creates no goal, starts no runtime, mutates no42bead and confers no standing authorization. The prompt drives work only when43a caller pastes it into their own goal runtime, under their own authority and44within the non-renewing envelope they set. Craft Goal reads tracker state when45present and needs no tracker installed to compile a prompt; the goal it writes46runs on one.4748Asked to craft ("craft a goal", "turn this into a goal"), return the decision,49then the filled prompt and settings when safe. Asked to lint ("lint/review50this goal", "is this safe"), return the decision and findings, plus a rewrite51when supplied facts permit one.5253## Admission: decide first5455**Fuzzy route is acceptable; fuzzy success is not.** Before goal creation the56caller must know the outcome, what evidence would prove it, non-goals,57authority, and the tracker the goal runs on (any with status, dependencies and58notes; BD is one); the exact experiment graph may still be unknown. Write each59terminal criterion as a Given/When/Then with an observable result and name60each domain term once; the caller can settle these with Interview first.6162- `USE_PLAN`: one shaped change with no verdict-driven follow-on; hand it to63 [Plan](../plan/SKILL.md) or native execution (RPI only if the caller selects it).64- `SAFE_TO_CREATE`: a terminal outcome that may need several related65 experiments, with those decisions and the budgets below supplied. A shaped66 goal with no beads may begin with 1 bounded discovery wave that creates the67 root and initial experiment beads.68- `UNSAFE_GOAL`: no falsifiable first question or terminal evidence can be69 named (route that intent to idea or plan work), or the request is indefinite70 monitoring or event reaction, which is an automation, not a terminal goal.7172Goals come in different sizes: size the wave and hard envelopes to the73outcome, never to one universal budget. Do not invent acceptance, authority,74graph semantics, tracker or campaign size; return `UNSAFE_GOAL` with the75missing decisions. The caller owns revision and goal creation.7677## What a safe goal holds7879- **Closed outcome, adaptive route.** Freeze terminal acceptance. New facts may80 change hypotheses and dependencies, never silently enlarge success.81- **Bead graph as memory.** The tracker is durable memory, not a parallel goal82 ledger: the root epic holds outer intent and each build bead one experiment,83 so compaction cannot erase the record. A decision bead resolves through the84 method Navigate names for it, not through a build.85 [Navigate](../navigate/SKILL.md) owns the walk each wave applies: graph86 contract, ratchet, discovery classes and checkpoint.87- **Proof stays outside the goal.** The goal consumes each verdict unchanged:88 orchestration cannot author its own proof. Fresh validation is for89 [Validate's costly cases](../validate/SKILL.md#when-a-fresh-judgment-is-worth-it)90 only, since a review per bead multiplies cost across the graph.91- **Two-level bounds.** Every experiment and every wave is bounded, and the92 whole goal has monotonic hard ceilings, so a new wave cannot mint a new93 campaign.9495The template's experiment policy and breaker carry these into the runtime.96They prevent the **completion treadmill**, where discoveries keep becoming97requirements and activity continues without new information, and98**first-red abandonment**, where one falsified hypothesis ends a viable99campaign.100101## Budgets and HOLD102103Declare both envelopes with numbers before any work is selected, helper and104validation costs included:105106- **Wave:** experiments, concurrency, wall time or tokens, live attempts, and107 a checkpoint at its end.108- **Goal:** total experiments, wall time or tokens, live attempts, compactions,109 and any patch or surface limit for the whole campaign.110111Name the native control that enforces each claimed hard limit and how the112remaining allowance is observed. Objective text is an instruction, not113enforcement: never report an unmeasured aggregate as a remaining balance, and114never claim the goal is paused from prose alone. No helper, retry, new115subject, compaction or wave renews the goal allowance.116117The template's **Breaker and helper** section is the one list of HOLD triggers118(implementation stops for causal review) and helper rules; fill its threshold119and keep every line.120121## Lint rubric122123| Dimension | Passes when the prompt |124|---|---|125| outcome | names one larger caller-visible result. |126| evidence | gives each terminal criterion as a Given/When/Then with its authoritative proof. |127| domain terms | defines each domain term once and reuses only that word. |128| admission | fits a goal: several related experiments, a falsifiable first question, a terminal finish. |129| bead graph | names the tracker and the root epic or its bounded bootstrap rule, and ties each experiment to an unmet criterion or named blocking uncertainty. |130| experiment boundary | makes one build bead one bounded experiment (native execution, or one RPI when the caller selects it; decision beads resolve as Navigate names), takes checks and CI as an ordinary bead's result, limits fresh validation to the costly cases and consumes verdicts unchanged. |131| ratchet | counts progress only as evidence tied to an unmet criterion or blocking uncertainty, never activity, counts or digests. |132| discovery | keeps all three classes (necessary-now, linked-follow-up, HOLD/rescope) and never downgrades a necessary-now discovery to linked-follow-up. |133| wave budget | sets numeric experiment, concurrency, time or token and live-attempt limits per wave, with a checkpoint. |134| hard budget | sets numeric campaign totals that nothing resets, naming the enforcing control or the unmeasured aggregate. |135| breaker | sets the numeric no-ratchet threshold and every HOLD trigger in the template's breaker. |136| helper | sends a requested acceptance change or operator-reserved decision straight to `NEEDS_OPERATOR`, allows at most one helper per other HOLD incident, maps `UNSTUCK` and `ESCALATE`, and stops implementation on `NEEDS_OPERATOR`. |137| scope | states non-goals and exact read, write, external and Git authority. |138| self-hosting | is n/a unless the goal repairs the factory (agent system) it runs on; then its authority repairs from an ordinary shell or worktree and runs that factory only as a declared bounded canary. |139| terminal reports | defines `ACHIEVED`, `NOT_ACHIEVED` and `NEEDS_OPERATOR`. |140141## Output142143Fill [the copy-paste-only goal prompt](references/goal-prompt.md): keep its144headings and terminal semantics and replace every angle-bracket field. Return,145in order:1461471. A first line that starts with exactly one decision: `SAFE_TO_CREATE`,148 `USE_PLAN` or `UNSAFE_GOAL`. `SAFE_TO_CREATE` judges prompt content; it does149 not certify native enforcement or create a goal.1502. For `UNSAFE_GOAL`, each missing decision; the caller can settle them with151 Interview.1523. When safe, the filled prompt; the settings: for each hard limit, the native153 control the caller sets to enforce it (such as the goal runtime's own token154 cap), or that it stays unmeasured; and the assumptions made, which cover155 only reversible wording or sourced facts. A number, criterion or authority156 the caller did not supply is a missing decision, never an assumption; label157 any suggested value a proposal.1584. Lint lines. In lint mode, one per rubric dimension: pass, n/a, or the159 finding. In craft mode, only the rows the draft still fails; each is a160 missing decision, so the decision cannot be `SAFE_TO_CREATE`.161162## Stop163164This skill makes one pass, craft or lint, then returns. It never creates or165runs a goal and never mutates beads. The goal it writes stops at its first166terminal report: `ACHIEVED`, `NOT_ACHIEVED` or `NEEDS_OPERATOR`.