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 restarter/lets-workflow --skill goal-testgit clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/restarter/lets-workflow/goal-test)<a href="https://agentmods.dev/skills/restarter/lets-workflow/goal-test"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/goal-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/restarter/lets-workflow/goal-test"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/goal-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 30 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 95 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00137 | $0.05782 |
| Opus 5.5 | $0.00055 | $0.02313 |
| Sonnet 5.5 | $0.00027 | $0.01156 |
| Haiku 4.5 | $0.00014 | $0.00578 |
Grade A, and why
goal-test 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 1mo 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal-test (local experiment)
/goal installs a session-scoped Stop hook with an LLM-evaluated termination condition. After every model turn, an evaluator-LLM reads the transcript and judges whether the goal is met. If not, the turn is rejected and the model must keep working. Best fit: convergent autonomous work (drive a task / epic / PR to a defined end state).
Not for periodic polling — that's /loop's job (see loop-test skill).
How /goal actually works
Sources: claude binary v2.1.150 strings + official docs (code.claude.com/docs/en/goal) + community write-ups (see References).
Mechanics
- User runs
/goal <condition>. Stored as session-scoped state. Cap: 4000 characters per condition. - After every model turn (assistant message that would normally yield), evaluator-LLM is invoked with the condition + transcript.
- Evaluator runs on your configured "small fast model" (Haiku by default). Eval tokens are billed separately; Anthropic describes them as "typically negligible" but they accumulate on long runs.
- Evaluator reads the transcript only — assistant text + user messages. Tool inputs/outputs ARE in transcript, but you must surface evidence in your assistant text for the evaluator to weight it heavily. "Quote specific text from transcript whenever possible" is in its system prompt.
- Evaluator returns JSON:
{"ok": true, "reason": "<quote evidence>"}→ goal achieved, session yields, UI shows✔ Goal achieved (Ns · N turn · N tokens)(user-visible only; not surfaced into assistant transcript — empirically confirmed Experiment 1).{"ok": false, "reason": "<why not>"}→ Stop hook rejects, model gets a system message and must continue. Common reason text:insufficient evidence in transcript.{"ok": false, "impossible": true, "reason": "..."}→ only when genuinely unachievable (self-contradictory condition, missing resource, exhausted approaches). Evaluator is instructed to NOT trust the model's self-assessment — it must independently judge whether the goal is structurally impossible.
- Hard cap:
CLAUDE_CODE_STOP_HOOK_BLOCK_CAPenv var (present in binary, undocumented publicly; the community-cited "500" comes from the unofficialjthack/claude-goalprecursor, not from official/goal). After N blocks the loop force-yields. Actual default unknown.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 281 lines · 137 tokens per session scan A cda95a72bb68
goal-test is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 5,782 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
deep-plan
Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
domain-modeling
A guide to defining and testing the important concepts and relationships in a software project's subject area, then recording the agreed vocabulary and decisions.
llm-eng-checks
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
codex-prompting
Internal guidance the stereo:codex-rescue subagent uses to compose prompts for Codex CLI models (coding, review, diagnosis, research); the main session does not load it.