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-fixgit 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-fix)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-fix"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-fix/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-fix"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-fix.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 | $0.00057 | $0.00816 |
| Opus 5 | $0.00028 | $0.00408 |
| Sonnet 5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
spectre-fix 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix
Standalone diagnosis-to-Execute bug workflow. Delegate diagnosis to spectre-fix-core; never implement.
Inputs
- bug_report (
$ARGUMENTS): error/stack trace, repro steps, context. If empty, ask the user for error message, repro steps, and relevant context before proceeding.
Working Set
- Resolve one managed
BUG_ROOT: an explicitly named managed root wins; otherwise load and followSkill(spectre-feature-root)withKIND=bugthrough DONE. Never adopt an ambient feature root. Keep writes beneath it and pass it unchanged. - The bug report plus the exact in-thread diagnosis and experience contract returned by
spectre-fix-core. - Affected paths, history, analysts, tests, and diagnostics are owned by the core and read just-in-time.
Outputs + DONE
The core's full diagnosis and experience contract rendered in-thread, mirrored in full into a self-locating managed repair plan at {BUG_REPORT_PATH} before code mutation, recording Bug, Bug Root, and the reported problem in the user's own words, plus an explicit Execute handoff. DONE when:
- Root cause and candidate repair boundary are grounded, not symptom-suppressed — name the cause and affected files.
- The transcript carries every contract row with its evidence; the plan beneath the managed bug root matches it. A file path is not a presentation.
- The current→expected experience, preserved invariants, and disclosed collateral changes are explicit; every row is resolved.
- The same response gives the exact bug-report path, explicit
fixorigin, and one copy-ready Execute invocation that works in a fresh session. - Command display is non-mutating; invoking Execute is the mutation boundary.
Method / guardrails
- Run
Skill(spectre-fix-core)with the bug report,PHASE=diagnose, and--orchestrated; requireDIAGNOSIS_READYand reject symptom-only explanations. - Present the experience contract first in product language: what users do and observe now, what they will do and observe after repair, and which adjacent journeys change or remain unchanged. Then present the root cause, affected files, repair boundary, and verification plan; resolve every
unresolvedrow. Mirror that render into{BUG_ROOT}/bug-report.md, using a scoped name if one already exists; capture the exact written path asBUG_REPORT_PATH; never alter canonical Scope or overwrite a reviewed plan. - In the same response, present one copy-ready host-specific
spectre-execute {BUG_REPORT_PATH} --origin fix. Never repair from Fix; invoking Execute is the mutation boundary. - Feedback revises the report and refreshes the command; it does not enter an approval loop.
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.
- today Changed · +5 lines · -21 tokens per session 4533dab79a38
- 5d ago Changed · -1 lines · -6 tokens per session 66b0ac9688fa
- 10d ago First seen · 43 lines · 84 tokens per session scan A a0a40c067f92
spectre-fix is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 816 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.