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 joenandez/spectre --skill spectre-goalgit clone --depth 1 https://github.com/joenandez/spectreWrote 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/joenandez/spectre/spectre-goal)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-goal"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-goal/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/joenandez/spectre/spectre-goal"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.01582 |
| Opus 5 | $0.00037 | $0.00791 |
| Sonnet 5 | $0.00015 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
spectre-goal 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal
Purpose
Write one autonomous completion contract whose success is provable by surfaced evidence. This is an explicit utility outside the default Plan → Execute route: spectre-plan never invokes it, and spectre-execute remains the sole implementation, repair, review, validation, and proof authority.
Inputs
$ARGUMENTS: finalized execute index or readable source plan plus itsexecution_state.md; optional target (Codex,Claude Code, orboth), turn/time cap, and--orchestrated.- Structured: reviewed plan, execute index, referenced tasks, and approved scope/UX/PRD when present. XL also requires completed task review with scope-safe Blocker/High findings integrated.
- Plan-direct: only readable plan/runtime inputs: a source plan plus its
execution_state.md, or a plan markedExecution Mode: direct; no execute/tasks artifacts or plan/task review required.
Working Set
- Reuse a managed
FEATURE_ROOTonly when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and followSkill(spectre-feature-root)through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged. - Structured source: execute index plus targeted task projections needed for objective, trace, acceptance, and verification; read run progress from
node "${PLUGIN_ROOT}/hooks/scripts/workflow-cli.mjs" run status, never from the task graph. Plan-direct source: plan, existing state, and its recorded scope/process manifest. GOAL_FILE={FEATURE_ROOT}/goal-prompts.md.
Outputs + DONE
GOAL_FILE contains exactly one copy-ready goal prompt. It starts with /goal : no title, preamble, manifest, selection note, rationale, or compact alternative. Put assumptions inside the relevant goal section.
Use this exact readable shape, substituting real values and preserving a blank line before and after every Markdown heading:
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.
- yesterday Changed · +5 lines 7b382454380e
- 6d ago Changed aded7131af50
- 12d ago First seen · 96 lines · 75 tokens per session scan A 79be0eaab605
spectre-goal is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,582 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…