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 NOMARJ/sigil --skill scan-packagegit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/scan-package)<a href="https://agentmods.dev/skills/nomarj/sigil/scan-package"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/scan-package/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/nomarj/sigil/scan-package"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/scan-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00114 | $0.00478 |
| Opus 5.5 | $0.00046 | $0.00191 |
| Sonnet 5.5 | $0.00023 | $0.00096 |
| Haiku 4.5 | $0.00011 | $0.00048 |
Grade A, and why
scan-package 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 11d 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.
What it actually says
Package Security Scan
Scan a package before installation:
-
Identify package type (pip or npm)
-
Run appropriate Sigil scan:
sigil pip <package>for Python packagessigil npm <package>for Node packages
Name a registry package (
requests==2.32.3,[email protected]). Sigil refuses paths, URLs and git specs, and fails when the PyPI releasepip installwould pick has no prebuilt wheel, because fetching those would run the package's own code before the scan. Report that to the user; never add--allow-build-scriptsorSIGIL_ALLOW_BUILD_SCRIPTSyourself (the hook asks the user before it runs; Sigil's own confirmation only guards against accidents, it does not tell you from a person, so the rule is yours to keep). For a file or directory already on disk, usesigil scan <path>instead. Sigil prints the version it scanned (resolves to …, andpackagein--format jsonand in the MCPscan_packageresult): install that exact version. -
Review quarantine findings
-
Recommend approve/reject based on risk score
Critical patterns to flag:
- Install hooks (setup.py cmdclass, npm postinstall)
- Eval/exec/pickle usage
- Network exfiltration (webhooks, DNS tunneling)
- Credential access (ENV vars, SSH keys)
- Code obfuscation (base64, charCode)
Present findings and guide the user through quarantine approval.
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.
- 11d ago Changed · +12 lines e670cdc751d9
- 1mo ago First seen · 26 lines · 114 tokens per session scan A a45a0ecec6c2
scan-package is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 12d ago), licensed Apache-2.0. It adds 114 tokens to every session and 478 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
sftp-cc
A natural-language SFTP tool for uploading local project files to a remote server. SFTP is a secure way to transfer files, and this tool supports incremental uploads, private-key binding, and permission fixes.
thread-list
Inspect or change the sidebar thread list's layout preferences: organization mode, sort, section order, hidden groups, collapsed groups, and thread row actions.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
workflows
Author or run durable BB workflows when the user requests workflow execution or multi-agent orchestration.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
url
Fetch and extract text from web URLs.