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 fp-checkgit 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/fp-check)<a href="https://agentmods.dev/skills/nomarj/sigil/fp-check"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/fp-check/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/fp-check"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/fp-check.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 | $0.00058 | $0.01545 |
| Opus 5.5 | $0.00023 | $0.00618 |
| Sonnet 5.5 | $0.00012 | $0.00309 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
fp-check 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
False Positive Gate Review
Adapted from Trail of Bits' fp-check skill. Every security finding must pass through this gate — no exceptions. Untriaged findings are worse than no findings, because they train the team to ignore alerts.
Why This Exists
Security scanners produce noise. When the noise-to-signal ratio gets too high, teams start ignoring findings entirely. The fp-check gate ensures every finding is classified, justified, and documented. The result is a security findings list where everything on it is real, and everything not on it was explicitly triaged and justified.
Hard Exclusion Rules
Before manual triage, automatically exclude findings matching these patterns. These are categories with near-zero signal in practice:
| # | Category | Exclude If |
|---|---|---|
| 1 | DOS / Resource Exhaustion | Finding describes denial of service, resource exhaustion, unbounded loops, or memory/CPU overload |
| 2 | Rate Limiting | Finding recommends adding rate limits without a concrete exploit path |
| 3 | Resource Leaks | Unclosed files, connections, or memory leaks — not security vulnerabilities |
| 4 | Open Redirects | Unless extremely high confidence with a concrete phishing scenario |
| 5 | Regex Injection / ReDoS | Injecting into a regex or regex DOS — not exploitable in practice |
| 6 | Memory Safety in Safe Languages | Buffer overflow, use-after-free, etc. in Rust, Go, Python, JS/TS, Java, C# |
| 7 | Test-Only Files | Findings in unit tests, test fixtures, or test helpers |
| 8 | Markdown / Documentation | Findings in .md files |
| 9 | SSRF (path-only) | SSRF that only controls the URL path, not host or protocol |
| 10 | Prompt Injection | User content in AI system prompts — not a code vulnerability |
| 11 | Log Spoofing | Unsanitized user input in logs (unless it logs secrets/PII) |
| 12 | Missing Audit Logs | Absence of logging is not a vulnerability |
| 13 | Outdated Dependencies | Managed by dependency scanning tools, not code review |
| 14 | Client-Side Auth | Missing permission checks in JS/TS client code — backend handles it |
| 15 | GitHub Action Workflow | Unless a concrete untrusted-input attack path exists |
| 16 | Shell Script Injection | Unless untrusted input provably reaches the injection point |
| 17 | Env Vars / CLI Flags | Treated as trusted values — attacks requiring their control are invalid |
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 First seen · 132 lines · 58 tokens per session scan A a23113505a30
fp-check is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,545 once invoked, about $0.0002 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.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
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.
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.