specter-delta

specter-delta is a skill for Claude Code, Codex from Samurai-goose/SPECTER-The-Illusive-Security-Protocol. It costs 48 tokens per session (1,305 once invoked), scanned A, original, MIT.

A quick security review of only the files changed since the previous Git commit, where Git is a tool for tracking code changes.

In plain words
What is it for?
It helps check changed code for issues such as missing input validation, unsafe permissions, prompt injection, data exposure, authentication bypasses, and weak handling of model output.
Why use it?
It limits the review to the latest work so common security issues can be found quickly before the task is considered finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .specter/scripts/findings_index.py add '<json-finding>'.

Good fit It helps check changed code for issues such as missing input validation, unsafe permissions, prompt injection, data exposure, authentication bypasses, and weak handling of model output.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Samurai-goose/SPECTER-The-Illusive-Security-Protocol
agentmods
npx agentmods add skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for specter-delta

README.md
[![agentmods](https://agentmods.dev/badge/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta/github.svg)](https://agentmods.dev/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta)
Your own site
<a href="https://agentmods.dev/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta"><img src="https://agentmods.dev/badge/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta/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.

agentmods 80×15 button for specter-delta

Your own site · 80×15
<a href="https://agentmods.dev/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta"><img src="https://agentmods.dev/badge/skills/samurai-goose/specter-the-illusive-security-protocol/specter-delta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.01305
Opus 5 $0.00024 $0.00652
Sonnet 5 $0.00010 $0.00261
Haiku 4.5 $0.00005 $0.00130

Measured 11d ago against content hash e49f6a452fdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

specter-delta 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.

specter-delta/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SPECTER Delta — Fast-Path Post-Task Audit

Purpose

Run a focused, time-boxed security review of only the files modified in the current task. Designed to execute quickly. Output is written to the persistent findings store for accumulation across sessions.

Trigger

  • .specter/.audit-pending file exists (written by scripts/post_task_audit.py hook)
  • User explicitly requests "delta audit" or "quick security check"
  • Before any task is marked as completed (enforced by specter.instructions.md)

Workflow

1. Read scope

Read .specter/.audit-pending to get the changed file list. If the file does not exist, run git diff --name-only HEAD directly. If that returns nothing, run git diff --name-only HEAD~1 HEAD.

2. Classify files

For each changed file, determine which checks apply:

File Pattern Checks to Apply
electron/ipc-handlers.* CWE-20: missing validation on new handlers; privilege boundary checks
electron/preload.* CWE-20: unvalidated IPC surface additions; contextBridge exposure
electron/ai-service.* Prompt injection, info disclosure, model output handling
electron/api-server.* Auth bypass, rate limiting, CORS, injection
components/**/*.tsx XSS, unvalidated event handlers, dangerouslySetInnerHTML usage
lib/**/*.ts Business logic, injection patterns, auth checks
**/auth*, **/login* AuthN/AuthZ weaknesses, session handling
**/db*, **/query* SQL/NoSQL injection, parameter binding
**/config*, **/.env* Secret exposure, insecure defaults
**/upload*, **/file* Path traversal, unrestricted upload
**/crypto*, **/hash* Weak algorithms, hardcoded keys

Only run checks relevant to each file's classification. Skip unrelated checks.

3. Run targeted checks

For each classified file:

  1. Read the file content
  2. Apply only the checks from the classification table above
  3. Look for:
    • Missing input validation at trust boundaries
    • Direct use of user-controlled data in sensitive operations
    • Missing authorization checks before privileged operations
    • Secrets or credentials in code or config
    • Calls to dangerous functions (eval, exec, dangerouslySetInnerHTML, etc.)
    • Any regression from a previous finding in findings/index.json

Read the full file on GitHub · 157 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. 11d ago First seen · 157 lines · 48 tokens per session scan A e49f6a452fdd

Subscribe to this mod's changes

specter-delta is a skill published in the GitHub repository Samurai-goose/SPECTER-The-Illusive-Security-Protocol (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,305 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 2026-08-31.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens