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 backendgit 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/backend)<a href="https://agentmods.dev/skills/transilienceai/communitytools/backend"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/backend/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/backend"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/backend.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 | $0.00384 |
| Opus 5.5 | $0.00016 | $0.00154 |
| Sonnet 5.5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
techstack-backend 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.
What it actually says
Backend Tech-Stack Identification
Scope
Identify server-side technologies: web servers (nginx, Apache, IIS), runtimes (Node, Python, PHP, Ruby, Java, .NET), backend frameworks (Express, Django, Flask, Rails, Laravel, Spring, ASP.NET), databases (Postgres, MySQL, Mongo, Redis), CMS (WordPress, Drupal, Magento), and API surfaces (REST, GraphQL, OpenAPI).
Signals (input)
- HTTP response headers —
Server,X-Powered-By,X-AspNet-Version,X-Drupal-*,X-Generator, etc. - Cookies — session-name fingerprints (
PHPSESSID,JSESSIONID,_rails_session, ...) - Error page bodies (404, 500)
- Path patterns hinting CMS (
/wp-admin/,/sites/default/) - API subdomains and OpenAPI/Swagger/GraphQL endpoints
robots.txtdirectives
Inferences (output)
- Web server + version
- Runtime / language + version
- Backend framework (with implied runtime)
- CMS + version
- Database (often indirect — via ORM dependency or hosted-DB DNS)
- API style (REST/GraphQL/gRPC) and authentication scheme
Techniques
When to use
- Phase 2/3 of a tech-stack OSINT engagement
- Mapping server-side attack surface (RCE, SSRF, deserialization)
- CVE matching by server + version
- Locating GraphQL / OpenAPI for follow-on api-security testing
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.
- 1mo ago First seen · 40 lines · 39 tokens per session scan A 2cd4ea44303e
techstack-backend is a skill published in the GitHub repository transilienceai/communitytools (591 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 384 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 2026-08-30.
Other skills, from other repositories
graphql-audit
GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a…
dns-pentesting
A guide to assessing DNS, the system that maps domain names to network addresses.
crypto-web-attack
A method for testing weaknesses in cryptography used by web applications, including padding-oracle flaws, weak randomness, predictable tokens, and hash length-extension opportunities. It also covers attacks against CBC and ECB block-based encryption.
kafka-attack
A security-testing guide for Apache Kafka, a system that stores and distributes streams of messages between applications. It focuses on brokers, topics, connectors, schemas, and access controls.
expression-language-injection
A guide to testing expression-language injection in frameworks such as Spring, Struts, Confluence, JSP, and JSF. Expression languages let applications evaluate specially formatted text as instructions.
xslt-injection
A methodology for testing XSLT injection, where attacker-controlled XML stylesheets alter how data is transformed. XSLT is commonly used to convert XML into HTML or other output formats.