qcoder-authorized-security

A guided process for carrying out and documenting security testing on systems where testing is explicitly authorized. It supports different security perspectives, including attack testing, defense validation, and collaboration between them.

In plain words
What is it for?
It verifies scope, discovers the available testing actions, gathers passive evidence, performs only the required active checks, records results and cleanup, and retests fixes when requested.
Why use it?
It keeps security work limited to an approved target, time window, and set of techniques. It also preserves evidence and separates observed facts from guesses.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/echoomegaprime/echo-qcoder/qcoder-authorized-security
Any agent
npx skills add echoomegaprime/echo-qcoder --skill qcoder-authorized-security
Clone the repo
git clone --depth 1 https://github.com/echoomegaprime/echo-qcoder

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.00558
Opus 5 $0.00039 $0.00279
Sonnet 5 $0.00016 $0.00112
Haiku 4.5 $0.00008 $0.00056

Measured yesterday against content hash 4743cd03c267, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qcoder-authorized-security 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 yesterday.

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.

qwen-skills/qcoder-authorized-security/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QCoder Authorized Security

Expected input

Identify the exact target, owner or authorization basis, allowed techniques, exclusions, time window, and desired evidence. Treat a color label as an operating perspective, not permission to expand scope.

Required sequence

  1. Read the ECHO pentester role, security modules, target repository instructions, and current scope record.
  2. Switch the durable SOL mission to pentester before active testing and read every returned context packet path.
  3. Discover the current scoped security capabilities through echo.caps.search or echo.caps.list; never guess a moving command contract.
  4. Validate scope before sending traffic. Begin with passive evidence, then perform the minimum active validation required by the objective.
  5. Route active operations through the signed and audited ECHO Prometheus/CRUCIBLE control plane. Supply exact confirmation tokens when a capability requires them.
  6. Preserve evidence, timestamps, target identity, tool result, and rollback or cleanup state. Separate observed facts from hypotheses.
  7. Remediate only when requested, then retest the immutable candidate and record residual risk.

Color routing

  • Blue: detection, hardening, containment, recovery, and control validation.
  • Red: scoped adversarial validation with explicit target and stop conditions.
  • Purple: paired attack and detection evidence with control improvement.
  • Orange, yellow, and green: use the definitions in the current ECHO pentester context packet; do not invent a target, identity, social pretext, or public action.

Third-party frameworks

CAI, PentestGPT, and Strix are research candidates, not automatic execution paths. Before adoption, pin a revision, review license and telemetry, inspect containers and tool permissions, run dependency and secret scans, and expose only bounded adapters behind the ECHO scope/confirmation layer. CAI requires separate commercial permission for professional or production use.

Stop conditions

Read the full file on GitHub · 40 lines

Changes

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.

  1. yesterday First seen · 40 lines · 79 tokens per session scan A 4743cd03c267

Subscribe to this mod's changes

qcoder-authorized-security is a skill published in the GitHub repository echoomegaprime/echo-qcoder (0 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 558 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens