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/samugit83/redamon/project-settings-cascadenpx skills add samugit83/redamon --skill project-settings-cascadegit clone --depth 1 https://github.com/samugit83/redamonWrote 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/samugit83/redamon/project-settings-cascade)<a href="https://agentmods.dev/skills/samugit83/redamon/project-settings-cascade"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/project-settings-cascade.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 | $0.00142 | $0.01137 |
| Opus 5 | $0.00071 | $0.00568 |
| Sonnet 5 | $0.00028 | $0.00227 |
| Haiku 4.5 | $0.00014 | $0.00114 |
Grade A, and why
project-settings-cascade 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Adding a new project setting, or changing the default value of an existing one.
This skill is the settings sub-pattern the tool/skill skills depend on; they link
here rather than restating it. For the surrounding tool wiring, see
agentic-tool-integration,
recon-tool-integration, or
builtin-agent-skill.
Critical Rules
- NEVER change a default in one layer only. A setting is synchronized across every layer in the table below. Update them in one commit or the UI and backend drift silently.
- NEVER assume existing projects pick up a new/changed default. A Prisma
@defaultapplies to new projects only. Existing rows keep their stored value; changing behaviour for them needs an explicit SQLUPDATE(ask before running it - it mutates every project). - NEVER share settings code between agent and recon.
agentic/project_settings.pyandrecon/project_settings.pyare separate modules with their own default dicts (DEFAULT_AGENT_SETTINGSvsDEFAULT_SETTINGS). A setting used by both is declared in both. - NEVER use
prisma migrate. This project is push-based:docker compose exec webapp npx prisma db push. - ALWAYS keep the name triad aligned: DB column
snake_case(via@map()), Prisma field + frontend + APIcamelCase, Python keySCREAMING_SNAKE_CASE. A mismatch meansfetch_*_settingsreadsNoneand silently falls back to the default. - ALWAYS give the frontend
onChangea fallback equal to the Python/Prisma default, so a project saved before the field existed does not writeundefined.
The layers (recon example: katanaTimeout)
| Layer | File | Form |
|---|---|---|
| DB / schema | webapp/prisma/schema.prisma | katanaTimeout Int @default(3600) @map("katana_timeout") |
| Python default | recon/project_settings.py:21 DEFAULT_SETTINGS (or agentic/project_settings.py DEFAULT_AGENT_SETTINGS) |
'KATANA_TIMEOUT': 3600 |
| Fetch mapping | recon/project_settings.py:863 fetch_project_settings (or fetch_agent_settings in the agent module) |
settings['KATANA_TIMEOUT'] = project.get('katanaTimeout', DEFAULT_SETTINGS['KATANA_TIMEOUT']) |
| Served defaults | recon_orchestrator/api.py:576 /defaults + RUNTIME_ONLY_KEYS |
include it, unless it is runtime-only (then add to RUNTIME_ONLY_KEYS) |
| Frontend | the tool's ProjectForm section component |
control with an onChange fallback equal to the default |
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 · 86 lines · 142 tokens per session scan A 25f97764e896
project-settings-cascade is a skill published in the GitHub repository samugit83/redamon (2,380 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 1,137 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
poc-validator
Proof-of-Concept (PoC) Validation Skill for security exploit verification. Use when validating exploitability of vulnerabilities, generating tailored payloads, executing exploits in sandboxed environments, or verifying successful exploitation (e.g., SQL injection, CVE exploitation, command injection). Triggers on…
redteam-sqli-detail-pack
Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.
implementing-api-rate-limiting-and-throttling
Implements API rate limiting and throttling controls using token bucket, sliding window, and fixed window algorithms to protect against brute force attacks, credential stuffing, resource exhaustion, and API abuse. The engineer configures per-user, per-IP, and per-endpoint rate limits using Redis-backed counters, API…
workflow-orchestrator
Module Loop and Iteration Skill for orchestrating multi-phase penetration testing workflows. Use when coordinating sequential tool execution, managing dependencies between reconnaissance and vulnerability scanning modules, implementing adaptive fallback strategies, or managing workflow state across iterations.…
Reconnaissance & OSINT Automation
Passive and active reconnaissance, subdomain enumeration, DNS analysis, technology fingerprinting, and OSINT data correlation for authorized security assessments.
research-orchestrator
Parallel research with 4 specialized agents (Official, Practical, Edge Cases, Future).