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 NicholasSpisak/goal-writer --skill goal-writergit clone --depth 1 https://github.com/NicholasSpisak/goal-writerWrote 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/nicholasspisak/goal-writer/goal-writer)<a href="https://agentmods.dev/skills/nicholasspisak/goal-writer/goal-writer"><img src="https://agentmods.dev/badge/skills/nicholasspisak/goal-writer/goal-writer/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/nicholasspisak/goal-writer/goal-writer"><img src="https://agentmods.dev/badge/skills/nicholasspisak/goal-writer/goal-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.03490 |
| Opus 5.5 | $0.00047 | $0.01396 |
| Sonnet 5.5 | $0.00024 | $0.00698 |
| Haiku 4.5 | $0.00012 | $0.00349 |
Grade A, and why
goal-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 2mo 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Writer
Two documents brief one round of autonomous agent work:
- Goal — the spine, hard-capped at 4,000 characters: what to do, what
to read first, the posture, the verification, the stop condition. Small
enough to paste directly into
/goalin Claude Code or Codex. - Rider — the prescriptive detail, unbounded (typically 10–35 KB): data schemas, phase plans, named depth tests, verb signatures, error footers, out-of-scope lists.
The pair is portable: the same two files brief Claude Code, Codex CLI, Cursor, or a human reviewer without modification. The slash command is the runtime; the pair is the spec. The pair compounds; the slash command does not.
The pair is also primitive-agnostic. A loop is an agent repeating
cycles of work until a stop condition is met, and /goal is one of four
loop types (turn-based, goal-based, time-based, proactive). /goal is
this skill's primary runtime, but the same two files feed a turn-based
verification skill, a scheduled /loop, or a proactive routine without a
rewrite — see references/harness-goal-commands.md.
Start with the simplest loop that fits the task.
This skill is project-agnostic. Substitute the project's own toolchain
commands wherever the templates say <project's ... command>.
When to use
- The user is starting a new round of agentic work and wants goal+rider
files written into the project's
docs/goals/(or equivalent). - Right scope: one feature, two to five files, half a day to a day of agent runtime.
When NOT to use: fifteen minutes of polish, a hot-fix, or a tiny PR — a five-line CSS tweak doesn't need eleven phases. The overhead only amortizes against rounds that would otherwise run hours of agent time.
Soft prerequisites — check, and tell the user what's missing:
- An architecture / AS-BUILT doc and a CHANGELOG. If absent, offer to write a minimal AS-BUILT first (one round, one rider, one phase).
- A fast test lane (~30 seconds). If the suite takes 40 minutes, the phase loop breaks down.
What ships with it
4 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.
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.
- 2mo ago First seen · 294 lines · 118 tokens per session scan A 628a57517941
goal-writer is a skill published in the GitHub repository NicholasSpisak/goal-writer (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 3,490 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 2026-08-31.
Other skills, from other repositories
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
civic-newsroom-plan
Plan an evidence-bound civic newsroom workflow with provenance, privacy, citation, correction, accessibility, and human publication gates.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
local-resource-index
Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.