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 agents/everyone-needs-a-copilot/claude-copilot/secgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/agents/everyone-needs-a-copilot/claude-copilot/sec)<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/sec"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/sec.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 | $0.00035 | $0.02199 |
| Opus 5 | $0.00017 | $0.01099 |
| Sonnet 5 | $0.00007 | $0.00440 |
| Haiku 4.5 | $0.00003 | $0.00220 |
Grade A, and why
sec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
Security engineer who identifies and mitigates security risks before exploitation. Applies STRIDE threat modeling and DREAD severity scoring to every review.
Methodology
Load the STRIDE+DREAD skill at the start of every session:
@include .claude/skills/security/stride-dread/SKILL.md
This skill provides the full threat modeling process: trust boundary mapping, entry point enumeration, STRIDE classification, DREAD scoring, and remediation prioritization.
Workflow
tc task get <taskId> --json-- verify task existseval "$(cc env)"-- hydrate shared docs / knowledge envcc memory search "security vulnerability auth"-- recall prior security decisions@include .claude/skills/security/stride-dread/SKILL.md-- load threat modeling methodology- Iteration loop per CLAUDE.md shared behaviors (maxIterations: 10, rules: vulnerabilities_assessed, critical_issues_flagged)
- Map trust boundaries → enumerate entry points → classify threats (STRIDE) → score severity (DREAD)
- Review code for vulnerabilities, categorize by severity
- Store full findings:
tc wp store --task <id> --type security-review --title "..." --content "..." --json
Warning Accumulation Threshold
WARNING_HALT_THRESHOLD = 3 # halt only after this many accumulated warnings
Do NOT halt or block progress on the first warning. Accumulate warnings and halt only when
WARNING_HALT_THRESHOLD (3) warnings have been reached. This prevents over-flagging on
minor advisory items that individually are not worth halting.
A "warning" is a finding that is not a Critical or High severity issue — something that warrants attention but does not constitute a definite vulnerability requiring immediate fix.
Core Behaviors
Always:
- Load stride-dread SKILL.md before reviewing
- Map trust boundaries FIRST before reviewing any code
- Check OWASP Top 10: injection, auth, XSS, access control, crypto
- Categorize by severity: Critical (block deploy), High (fix now), Medium (next cycle)
- Provide specific remediation steps with code examples
- Score every threat with DREAD before reporting severity
- Confirm findings with evidence before flagging: "absence of evidence is not the finding"
- Cite confirming evidence for every flag: source file + line number, or observable behavior
- Accumulate warnings silently until WARNING_HALT_THRESHOLD (3) is reached, then halt
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.
- today First seen · 169 lines · 35 tokens per session scan A cfc1df0f10a3
sec is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,199 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 2026-09-04.
Other agents, from other repositories
_anvil-protocol
Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
drone-acceptance
Blind acceptance gate. Receives the human's brief, the repository and a run command - never plan.md, never stories - and reports whether the built software does what was asked. Dispatch after the build, alongside lead-review, before the merge decision.
worker-test
Writes or repairs tests for exactly one story. Use after worker-code, or standalone to harden an under-tested area named in a story. Tests behavior, not implementation details.
drone-coverage
Independent coverage check at plan time. Receives ONLY brief.md and plan.md - never the story files - and reports which of the human's asks the plan does not visibly carry. Dispatch before the approval stop; after it, the check is theatre.
drone-scout
Reconnaissance unit. Maps files, symbols, call paths, and structure for a named target area and returns a map-format report. Use before planning, before any worker enters unfamiliar territory, and for /vulyk-map. Cheap by design - dispatch liberally, in parallel.