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 ashfulcra/fulcra-tools --skill sealed-secretsgit clone --depth 1 https://github.com/ashfulcra/fulcra-toolsWrote 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/ashfulcra/fulcra-tools/sealed-secrets)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/sealed-secrets"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/sealed-secrets/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/ashfulcra/fulcra-tools/sealed-secrets"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/sealed-secrets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 449 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00049 | $0.06550 |
| Opus 5 | $0.00024 | $0.03275 |
| Sonnet 5 | $0.00010 | $0.01310 |
| Haiku 4.5 | $0.00005 | $0.00655 |
Grade A, and why
sealed-secrets 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 9d 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 — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sealed Secrets
A successor session on a fresh machine must be able to recover the role's credentials — and must never be told a revoked one is fine.
Agents lose their machines. Containers get reclaimed, hosts are rebuilt from snapshots, a session resumes tomorrow on hardware that has never seen your config. Everything else an agent needs can live in a shared object store. Its credentials cannot — not in the clear, because the store is readable by every agent on the team and by whoever operates it.
So seal them. The store carries ciphertext; the operator carries one passphrase; the successor runs one command and learns, per secret, whether it actually works.
A decrypt that succeeds is not a credential that authenticates.
That sentence is the whole design. A bundle that decrypts perfectly to a revoked token passes every cryptographic check and still leaves the successor dead.
Where to start — the re-entrancy probes
Run in order; enter at the first probe that fails. Every state below is safe to re-enter: sealing is a new bundle version, unlocking is read-only, and verifying makes no writes at all.
| Probe (run in order) | Command | Passes when | If it fails, enter at |
|---|---|---|---|
| 1. Role has a bundle pointer | read the role's charter frontmatter | a sealed_bundle: key is present and non-empty |
§1 Seal |
| 2. Bundle object exists | read the path that key names | the read returns an object (not absent, not an error) | §1 Seal — the pointer is dangling |
| 3. Envelope parses | parse it as JSON | it has schema, wraps (non-empty list), payload |
§1 Seal — re-seal; do not hand-edit |
| 4. You can open it | run the unlock command | it prints a per-secret table, no crypto errors | §2 Unlock |
| 5. The secrets WORK | read that same table | every secret reads VERIFIED |
§3 When verify fails |
Probe 5 is the only one that matters to the caller. Probes 1-4 can all pass on a bundle full of revoked credentials. Never report "unlocked" as success; report the verify table.
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.
- 9d ago First seen · 530 lines · 49 tokens per session scan A 6295e33154eb
sealed-secrets is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 6,550 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 2026-08-31.
Other skills, from other repositories
magic-compact
Compact this Claude Code session.
citation-intelligence
Use when the user wants to know which URLs AI engines cite for a query, whether their domain is being cited by ChatGPT/Claude/Perplexity/Gemini/Google AI Overviews/Bing, what queries their site is cited for, how citation rate changes over time, or how their citation coverage compares to competitors. Self-hosted, BYO…
proof-engine
Create formal, verifiable proofs of claims with machine-checkable reasoning. Use when asked to prove, verify, fact-check, or rigorously establish whether a claim is true or false — mathematical, empirical, or mixed. Trigger phrases: "is it really true", "can you prove", "verify this", "fact-check this", "prove it"…
join
Join the Cortex agent team — reads agent config from team directory, generates .cortex.md protocol, updates CLAUDE.local.md. Idempotent — safe to re-run as a sync.
setup
First-time Cortex setup — creates team directory, config, and chief of staff agent.
leave
Leave the Cortex agent team — removes .cortex.md, cleans CLAUDE.local.md, sets agent status to inactive in team directory.