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-scopegit 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-scope)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-scope"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-scope/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-scope"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-scope.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 | $0.00076 | $0.01380 |
| Opus 5 | $0.00038 | $0.00690 |
| Sonnet 5 | $0.00015 | $0.00276 |
| Haiku 4.5 | $0.00008 | $0.00138 |
Grade A, and why
spectre-scope 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scope
Turn an unstructured request into clear scope boundaries (IN / OUT / ANTI-SCOPE), user value, load-bearing assumptions, and decisions — clear on WHAT, silent on HOW. Boundaries and user value first; defer all technical/implementation questions to spectre-plan.
Inputs
$ARGUMENTS— the feature/problem brain-dump. If empty → greet, ask for context, and WAIT for the user.- Existing root/artifact: context for new work; reuse only for the same scope run,
FROM_KICKOFF=true, or explicit resume/re-scope. On re-scope, readconcepts/scope.mdfully, surface settled decisions and the delta, and confirm before rewriting the immutable downstream anchor. FROM_KICKOFF=true+KICKOFF_DOC→ read the doc, extract (Core Problem, User Value, Decisions Made, Remaining Ambiguities, Key Code Refs), then skip grounding + exploration and go straight to clarifications. Already-grounded.
Working Set (late-bound — read at run-time, never inline)
FEATURE_ROOT = .spectre/features/<feature-name>/, resolved from the input or proposed below.- captured session or current thread memory for this area, if present
Feature root contract
- 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.
Method / guardrails
- Reply before tools. Acknowledge first; never go silent to "think." No tool calls in the opening reply except reading
KICKOFF_DOCwhenFROM_KICKOFF=true. - WHAT, not HOW. Ask only about boundaries, user value, and anti-scope. Defer architecture/trade-offs/integration to
spectre-plan. Exception: scope that is inherently technical (e.g. "migrate DB X→Y"). - Ground once. Start with exactly one fast lookup to anchor the hypothesis in repo reality — a single
@spectre_finderquery, or onegrep/glob; skip it if slow. Needing broader grounding exceeds this fast scope pass. - Lead with a grounded hypothesis (problem, who it affects, proposed feature name/root, IN / OUT / ANTI-SCOPE) and 5–8 questions tagged (blocking) / (optional). Iterate boundaries (IN / OUT / ANTI-SCOPE / Unsure) until confirmed, then clarify remaining ambiguity with
AskUserQuestion(≤4 at a time). No clarification files.
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.
- 4d ago Changed · -1 lines 705b09908229
- 10d ago First seen · 69 lines · 76 tokens per session scan A e4b7d5a99656
spectre-scope is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,380 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…