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-learngit 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-learn)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-learn"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-learn/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-learn"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 10 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00066 | $0.00792 |
| Opus 5.5 | $0.00026 | $0.00317 |
| Sonnet 5.5 | $0.00013 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
spectre-learn 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learn
Purpose
Turn an explicit user capture request into maintained knowledge or a historical work-record request. Learn owns user intent and routing; Skill(spectre-capture) owns knowledge persistence and Skill(spectre-work-record) owns work history. Do not revive knowledge-skill authoring, proposal gates, dossiers, or SessionStart output.
Inputs
- An explicit user capture request,
$ARGUMENTS, and the current conversation; bare invocation means review the conversation for consequential, evidenced knowledge. - User intent: an insight or correction targets maintained knowledge; a work summary, explicit snapshot, or historical correction targets a typed work record.
- The current project directory and any exact record/work identity already in context. A Spectre feature root is not required.
Working Set
- Search metadata and exact verified loads needed to identify a maintained record or answer a stated work question.
- Current evidence. An explicit user statement that a lasting decision is current, corrected, or superseded is accepted authoritative evidence for that decision. Investigate only genuinely missing material evidence; do not seek independent corroboration or reconfirmation for that statement, reconstruct a conversation, or manufacture a durable fact.
Outputs + DONE
Skill(spectre-capture)orSkill(spectre-work-record)returns a saved, updated, or no-op result. Report its record kind, exact ID, and outcome.- A broad account always uses the seven-section work record form. No Learn output creates a knowledge skill, separate dossier, or SessionStart entry.
- DONE when qualifying evidence has reached Capture or bare Learn truthfully reports a no-op.
Method / guardrails
- Identify intent from the request. A bare request scans the conversation for accepted consequential decisions, verified reusable constraints, corrections, or confirmed blockers/resolutions. An explicit user correction is already-authorized evidence, not an unsupported hypothesis; routine progress and model-generated hypotheses are no-ops.
- For an insight or correction, provide
Skill(spectre-capture)the evidence, authority, and maintained-knowledge target. For an explicit user correction, cite that direction as evidence, revise the current record, and retain disagreeing repository statements only as stale or historical context; absence of repository corroboration is not missing evidence. For work summary, explicit snapshot, or historical correction, provideSkill(spectre-work-record)the exact run/PR/candidate association and only truthful lifecycle facts. - The knowledge skill reads
${PLUGIN_ROOT}/skills/spectre-capture/references/knowledge-capture-input.json; the work-record skill readsspectre-work-record/references/work-capture-input.json. Each owns construction, revisions, tags, saving, and recovery. Learn does not duplicate that SOP or write records. Already-authorized facts need no new proposal or approval loop.
What ships with it
3 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.
- 1mo ago Changed a72f2d02dca1
- 1mo ago Changed · -48 lines · -27 tokens per session d2e036c91342
- 1mo ago Changed · +6 lines 13e0e676b7b2
- 2mo ago First seen · 91 lines · 93 tokens per session scan A 737b0c0ca62d
spectre-learn is a skill published in the GitHub repository joenandez/spectre (164 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 792 once invoked, about $0.0003 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 2026-08-30.
spectre-learn compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spectre-learnjoenandez/spectre | Skill | 164 | 1mo ago | MIT | A | 66 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |