contextual-stewardship

contextual-stewardship is a skill for Claude Code, Codex from lindoelio/spec-driven-steroids. It costs 104 tokens per session (2,399 once invoked), scanned A, original, MIT.

A knowledge system for recording and retrieving project decisions, business rules, and workflows, with their sources and lifecycle. It organizes guidance into areas such as architecture, security, performance, and team responsibilities.

In plain words
What is it for?
It is for documenting technology choices, product rules, testing or Git practices, security policies, compliance needs, ownership, and technical debt. Custom categories can also be used.
Why use it?
It prevents important decisions and rules from being lost across conversations and projects. It helps an agent use existing context before making or implementing a new decision.

Skill for Claude CodeCodex

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

Good fit It is for documenting technology choices, product rules, testing or Git practices, security policies, compliance needs, ownership, and technical debt. Custom categories can also be used.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lindoelio/spec-driven-steroids/contextual-stewardship
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.

Any agent
npx skills add lindoelio/spec-driven-steroids --skill contextual-stewardship
Clone the repo
git clone --depth 1 https://github.com/lindoelio/spec-driven-steroids

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 contextual-stewardship

README.md
[![agentmods](https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/contextual-stewardship/github.svg)](https://agentmods.dev/skills/lindoelio/spec-driven-steroids/contextual-stewardship)
Your own site
<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/contextual-stewardship"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/contextual-stewardship/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 contextual-stewardship

Your own site · 80×15
<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/contextual-stewardship"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/contextual-stewardship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,399 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 63
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • medium Rogue Agent · line 92
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00104 $0.02399
Opus 5 $0.00052 $0.01200
Sonnet 5 $0.00021 $0.00480
Haiku 4.5 $0.00010 $0.00240

Measured 10d ago against content hash 8935d497ab08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

contextual-stewardship 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 10d 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.

packages/cli/templates/universal/skills/contextual-stewardship/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contextual Stewardship Skill

You are acting as a Staff Engineer responsible for Contextual Stewardship — a knowledge graph system that captures, retrieves, and manages architectural decisions, business rules, and workflows across projects with full provenance tracking and lifecycle management.

Core Concepts

Domains

All rules are classified into one of 8 standard domains:

Domain Description
architecture Tech stack choices, design patterns, ORM preferences, library decisions
business Product rules, target audience, domain logic, business constraints
workflow Git patterns, testing rules, naming conventions, team processes
security Security policies, authentication patterns, data protection rules
performance Performance budgets, caching strategies, optimization guidelines
legal Compliance requirements, licensing constraints, regulatory rules
team-structure Ownership, roles, responsibilities, escalation paths
technical-debt Known debt items, refactoring priorities, modernization plans

Custom domains are also supported — any string not in the standard list is accepted as a custom domain. Child domains inherit from their parent (e.g., architecture.database inherits from architecture).

Lifecycle States

Rules transition through three states:

  • active — Rule is currently in effect
  • deprecated — Rule is superseded by another; supersededBy link is set
  • archived — Rule is no longer relevant; preserved for historical reference

Storage Backend

The system uses JSON file storage for all rule persistence:

Backend Storage Location
json-graph ~/.agents/stewardship/global/{state}/ and ~/.agents/stewardship/projects/{project-id}/{state}/ JSON files

CLI Commands

All stewardship operations use the sds stewardship CLI command. Ensure sds (spec-driven-steroids) is installed and available in PATH.

Read the full file on GitHub · 243 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. 10d ago First seen · 243 lines · 104 tokens per session scan A 8935d497ab08

Subscribe to this mod's changes

contextual-stewardship is a skill published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 2,399 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 2026-08-30.

Related

Other skills, from other repositories

artifact-conventions

Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.

attilaszasz/sdd-pilot · 59 tokens

plan-authoring

Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.

attilaszasz/sdd-pilot · 41 tokens

task-generation

Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.

attilaszasz/sdd-pilot · 35 tokens

adr-authoring

Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.

attilaszasz/sdd-pilot · 30 tokens

implementation-standards

Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.

attilaszasz/sdd-pilot · 44 tokens

spec-authoring

Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.

attilaszasz/sdd-pilot · 40 tokens