Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MAX0MAX/goal-driven --skill goal-contract-writergit clone --depth 1 https://github.com/MAX0MAX/goal-drivenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/max0max/goal-driven/goal-contract-writer)<a href="https://agentmods.dev/skills/max0max/goal-driven/goal-contract-writer"><img src="https://agentmods.dev/badge/skills/max0max/goal-driven/goal-contract-writer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00794 |
| Opus 5 | $0.00022 | $0.00397 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
goal-contract-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Contract Writer
Overview
goal-contract-writer turns ambiguous work into a standard Goal Contract.
Clarify only what is required to define the work. Then return the canonical contract. Conversation is not the product.
This skill does not implement, run, or manage a Goal-Driven agent loop. It defines the upstream contract that a loop, workflow engine, host goal system, or human operator can execute and verify.
goal-contract-writer is the only normal user-facing entrypoint. The paired goal-contract-verifier skill exists for runtimes or operators that need fresh-subagent verification of execution state, but verifier behavior is not part of this skill's required output.
When to Use
Use this skill when:
- the request has a concrete outcome but starts ambiguous
- the next agent, system, or person needs a stable goal artifact
- success must be judged by observable evidence
Do not use it for open-ended ideation or as a replacement for execution workflows.
Core Output
Produce exactly one canonical artifact:
Goal Contract
Goal Contract must contain exactly these fields:
goalscopesuccess_criteriaevidenceguardrails
Do not add runtime verdicts, adapter metadata, or workflow prose to the contract body.
Use references/canonical-goal-contract.md for the canonical contract schema.
Contract Generation Flow
- Clarify until
goalandscopecan be written without guesswork. - Write
success_criteriathat fully cover thegoaland can be checked without subjective judgment. - Write matching
evidencethat proves or disproves each criterion without adding hidden acceptance rules. - Record
guardrailsthat prevent scope drift, unsafe assumptions, or missing approvals. - Return the canonical Goal Contract and stop.
Use references/contract-elicitation-protocol.md for clarification rules and examples/ for concrete model contracts.
Hard Rules
- Do not replace the contract with free-form advice or host-specific prose.
- Do not use subjective completion language.
- Do not add verifier workflow, execution routing, owners, priorities, or next steps to the canonical contract.
- Do not let
evidencesmuggle in acceptance rules that are missing fromsuccess_criteria. - Do not let any adapter redefine the canonical contract fields.
- Do not continue into planning or execution unless the user explicitly starts a separate task.
- Keep the contract execution-neutral.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 257 B
- examples/bugfix-empty-csv-export.md 3.2 KB
- examples/feature-dark-mode-settings.md 3.3 KB
- examples/planning-job-search.md 2.9 KB
- examples/README.md 621 B
- examples/research-stripe-vs-paddle.md 2.9 KB
- INSTALL.md 13 KB
- references/canonical-goal-contract.md 4.7 KB
- references/contract-elicitation-protocol.md 2.7 KB
- references/downstream-adapters.md 6.0 KB
- references/evidence-patterns.md 5.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 92 lines · 43 tokens per session scan A 46db921d720a
goal-contract-writer is a skill published in the GitHub repository MAX0MAX/goal-driven (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 794 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stats
Query or render the state of the scattered kit/tide/tg-cleanup/learned ledgers (the dwarves-kit gate/proof/telemetry corpus, tide file-move state, tg-cleanup snapshots, the learning ledger), and detect + propose backlog rows off anomalies in that state. Use when the operator asks to SEE ledger state -- "show me the…
topology-drift
Maintainer-only (dwarves-kit repo dev only). Use to audit THIS KIT's OWN feature estate against its path map, "run the topology-drift loop", "is the workflow path map still complete", "does every feature appear in workflow-paths", "feature inventory drift", or after a batch of merges that added/removed commands…
observe
Query and render the kit's control plane from an agent session. Use when asked about the fleet's runs, gate verdicts, conformance, spend/tokens/cache economics, the cognitive-debt score, replaying a recorded run, benchmark results, or building/refreshing the observability dashboard. Trigger phrases include…
get-api-docs
Fetch curated API documentation using Context Hub (chub) before coding against any external API. Use when the task involves calling a third-party API (Stripe, OpenAI, Airwallex, Notion, etc.) to prevent hallucinated parameters and deprecated endpoints.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.