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-create_plangit 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-create_plan)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-create_plan"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_plan/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-create_plan"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_plan.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 | $0.00037 | $0.01217 |
| Opus 5 | $0.00018 | $0.00609 |
| Sonnet 5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
spectre-create_plan 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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create_plan
Purpose
Turn confirmed Scope into the smallest correct implementation plan. Behavioral scope is binding; implementation means are not. The primary owns synthesis and plan.md; research agents return evidence only.
Inputs
$ARGUMENTS: confirmed Scope—thread, root, or descendant—plus--depth {xs|light|standard|comprehensive}(defaultstandard),--no-review, and--execution {direct|structured}(defaultstructured).- Existing scope/PRD/UX and substantive
task_context.mdresearch. Orchestrated calls reuse router research; never redispatch it.
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. Repair touched stale metadata. - Read repository rules and real code. Reuse evidence first; otherwise use
@spectre_finder,@spectre_analyst, and@spectre_patternsonly for unresolved material questions. They do not write planning artifacts. - Treat confirmed IN/OUT/ANTI-SCOPE, success criteria, constraints, and approved design as authoritative. Never silently change them.
Outputs + DONE
Write {FEATURE_ROOT}/specs/plan.md, self-locating below its title with Feature: and Feature Root: derived from the physical directory. Add Execution Mode: direct for --execution direct or --depth xs.
Every plan contains:
- Overview — requested outcome and smallest viable solution shape.
- Technical Approach — thinnest end-to-end path, current data flow, closest
file:linereuse anchors, decisions, and any complexity exceptions. - Critical Files — 1–7 verified files tagged Core logic / Pattern / Interface / Test.
- External Dependencies — Verify Before Implementation — exact package versions plus existence commands, or
No new packages. - Verification — How We Know This Works — 1–3 falsifiable test/observable/state signals per major behavior; direct-mode signals are executable.
- Out-of-Bounds — DO NOT add — carry forward canonical OUT/ANTI-SCOPE and only evidence-backed technical exclusions; never pad a generic list.
- Risks & Filled Assumptions — current credible risks with minimum mitigation or accept-and-monitor; silent-spec defaults only.
- Routing Observations — exact
## Routing Observationsheading with workstream count, independent workstreams, dependency sequencing, shared-contract consumers, staged rollout/migration, new abstraction, unresolved material decision, and observed uncertainty; observations only, never route selection.
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.
- today Changed · +6 lines 98d7df8a949e
- 5d ago Changed b1ce568732fe
- 6d ago Changed · -7 lines · -60 tokens per session 3bd69d398837
- 10d ago First seen · 67 lines · 97 tokens per session scan A 0d6716c3f0ea
spectre-create_plan is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,217 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 2026-08-30.
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…