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 agentmods add skills/evilfreelancer/secs/performing-social-engineeringnpx skills add EvilFreelancer/secs --skill performing-social-engineeringgit clone --depth 1 https://github.com/EvilFreelancer/secsWrote 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/evilfreelancer/secs/performing-social-engineering)<a href="https://agentmods.dev/skills/evilfreelancer/secs/performing-social-engineering"><img src="https://agentmods.dev/badge/skills/evilfreelancer/secs/performing-social-engineering.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01520 |
| Opus 5 | $0.00053 | $0.00760 |
| Sonnet 5 | $0.00021 | $0.00304 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
performing-social-engineering 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performing Social Engineering
Social engineering tests the one control you cannot patch: people. Done right, it measures how a real lure would fare against the organization's training, email controls, and reporting culture, and it produces the metrics and teachable moments that actually move that culture. Done wrong, it humiliates employees, leaks real personal data, or crosses into fraud. The line between the two is authorization and restraint, so this skill is gated harder than most.
Authorization here is organizational and specific: written executive sign-off, legal clearance, a defined scope (which groups, which vectors, which exclusions), and HR/legal coordination for how results are handled and disclosed. Per AGENTS.md you target a consenting organization's controls, not non-consenting private individuals; you never misattribute the campaign to a real named third party (no false flag); and you demonstrate susceptibility without causing real loss. Assume every phish is LOUD and will be reported — that is the point.
When to Use
- The engagement explicitly authorizes testing people, with executive sign-off
- Developing a pretext and phishing/spearphishing campaign against in-scope groups
- Vishing or smishing scenarios to test help-desk and verification procedures
- Physical pretexting (tailgating, USB drops) where the ROE permits it
- Producing susceptibility metrics and awareness recommendations
When NOT to Use
- Analyzing an inbound phishing email defensively — use
analyzing-phishing-emails - OSINT and target-surface mapping only — use
performing-reconnaissance; come here to weaponize it into a pretext - Building the credential-harvesting landing page's web flaws — use
testing-web-applications - Any test of non-consenting individuals or without org sign-off — refuse and escalate; scope on paper for an individual is not consent
- Writing up results — use
reporting-security-findings
Method (authorization-gated at every phase)
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.
- 4d ago First seen · 113 lines · 105 tokens per session scan A 9760fae4d0ee
performing-social-engineering is a skill published in the GitHub repository EvilFreelancer/secs (10 stars, last pushed 25d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,520 once invoked, about $0.0005 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
Blue Team Defense & Hardening
System hardening, detection engineering, security baseline monitoring, patch management, defense-in-depth architecture, and security posture improvement.
wave-issue-coverage
For each DRAFT requirement in a given Ground Control wave (or all waves), ensure a GitHub issue covers it and is bidirectionally linked. Use when the user asks to "cover wave N requirements with issues", "back-fill issues for draft requirements", or similar. Requires the Ground Control MCP and gh CLI.
ship
Ship current branch — CI, SonarCloud, code review, security review, fix all issues, merge. Assumes code is already committed and pushed.
create-huntable-agent
Add a new extraction sub-agent to Huntable CTI Studio as a first-class peer of CmdlineExtract, ProcTreeExtract, HuntQueriesExtract, RegistryExtract, ServicesExtract, and ScheduledTasksExtract. Use this skill whenever the user asks to "add a new agent", "create a sub-agent", "wire up a new extractor", "add a new…
codebase-test-trueup
Audit test coverage gaps and generate unit tests to close them. Use when the user says "test trueup", "coverage gaps", "test coverage audit", "fill coverage", "write missing tests", "backfill tests", "scope tests", "test what I changed", or any request to identify and fill test gaps. Three modes: audit (report only)…
mdu
Update all Markdown documentation to reflect code and session changes. Use this skill whenever the user says "mdu", asks to "update docs", "sync documentation", "refresh changelog", "update the changelog", "docs are stale", "add this to the changelog", or any request to align documentation with recent code changes.…