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 transilienceai/communitytools --skill risk-prioritisergit clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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/transilienceai/communitytools/risk-prioritiser)<a href="https://agentmods.dev/skills/transilienceai/communitytools/risk-prioritiser"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/risk-prioritiser/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/transilienceai/communitytools/risk-prioritiser"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/risk-prioritiser.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 | $0.00039 | $0.01681 |
| Opus 5 | $0.00019 | $0.00840 |
| Sonnet 5 | $0.00008 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
risk-prioritiser 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Prioritiser
Consume the attack-path graph + the client-supplied business-tier map and emit a single ranked list of paths the org should remediate first. Mounted onto cloud-agent task #7.
Trigger
Cron daily after attack-path-stitcher (task #6) completes. Also event-fires when a new validated/*.json is written with nvd.score >= 9.0.
Workflow
- Load inputs.
artifacts/attack-paths.json— graph from task #6. Split intoconfirmed_paths(RFP-grade) andinferred_paths(topology/supply-chain).business-tier-map.csv— client-supplied asset → tier. Search order:{OUTPUT_DIR}/business-tier-map.csv→projects/rfp-3.3/schemas/business-tier-map.csv.
- Score each
confirmed_pathsentry.feasibility= product of every edge'sfeasibilityalong the path. For confirmed paths this is always 1.0.technical_severity=max_cvss_along_path / 10.business_impact= tier weight of the destination (crown_jewel = 1.0 by definition).entry_exposure= 1.0 if entry node isexternal: true, else 0.5.- Final score =
feasibility × technical_severity × business_impact × entry_exposure.
- Score each single-asset validated finding that does not sit on a confirmed path. Same formula;
feasibility = 1.0,business_impact= asset's own tier weight, hop count = 1. - Score each
inferred_pathsentry, but cap their bucket placement attheoreticalregardless of numeric score. Inferred paths NEVER reachimmediate/short_term/medium_term— RFP §3.3 requires "confirmed", and inferred paths are evidence-deficient by construction. - Sort descending. Stable tie-break order: max CVSS desc → hop count asc → finding age desc (newer first).
- Bucket into roadmap tiers.
immediate(0-7 days): confirmed AND score ≥ 0.6short_term(7-30 days): confirmed AND 0.3 ≤ score < 0.6medium_term(30-90 days): confirmed AND 0.1 ≤ score < 0.3monitor: confirmed AND score < 0.1theoretical(track-only): any path withpath_class != "confirmed". Surfaced in board reports but excluded from the remediation SLA roadmap.
- Write outputs to
artifacts/attack-paths-ranked.json+attack-paths-ranked.md. Each row carriespath_classso downstream consumers can filter.
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.
- 11d ago First seen · 122 lines · 39 tokens per session scan A 61ccb9b8aab9
risk-prioritiser is a skill published in the GitHub repository transilienceai/communitytools (520 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,681 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 2026-08-30.
Other skills, from other repositories
credential-attack
Password spray methodology for bug bounty — when to do it vs web-vuln hunting, the wordlist-gen + breach-check + osint-employees + spray pipeline, mode selection (http-form / oauth / o365 / okta), rate-limit + lockout tactics, BBP legal guardrails, success detection, and the spray → authenticated /hunt chain pattern.…
report-writing
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use…
triage-validation
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer…
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
web2-recon
Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when…
security-expert
Expert-level application security, OWASP Top 10, penetration testing, and security best practices. Use when the user mentions OWASP, pentesting, appsec, vulnerability, encryption, or authentication, or when the task involves Security Principles, OWASP Top 10, Security Domains, or Broken Access Control.