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.
git clone --depth 1 https://github.com/ntorga/agent-starter-kitnpx agentmods add skills/ntorga/agent-starter-kit/context-maintenanceWrote 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/ntorga/agent-starter-kit/context-maintenance)<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/context-maintenance"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/context-maintenance/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.
<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/context-maintenance"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/context-maintenance.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.01108 |
| Opus 5 | $0.00012 | $0.00554 |
| Sonnet 5 | $0.00005 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
context-maintenance 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Every directory in a project has a .context.md that orients whoever arrives next — human or agent. The project also keeps a single docs/FEATURE-MAP.md — a feature index that maps every user-facing feature to the code path that implements it. Together, .context.md files answer "what lives here" and the feature map answers "how does this feature work end-to-end." This skill defines when and how to keep both accurate as the project evolves, and the schemas they must follow.
Procedure
.context.md
-
Scan. List directories that need a
.context.mdcreated or updated:bash .agents/skills/assets/context-scan-directories.shThe script prefers
src/as root, skips hidden and vendored directories, and outputs only directories where.context.mdis missing or stale (files newer than the existing.context.md). Pass an explicit root to narrow the scan:bash .agents/skills/assets/context-scan-directories.sh path/to/root. -
Write or update the
.context.mdusing this schema:<context path="relative/path" updated="YYYY-MM-DD"> One to two sentences describing what this directory contains and why it exists. ## Summary - filename.ext — short description of what this file does - filename.ext — short description of what this file does - subdirectory/ — short description of what this subdirectory contains ## Constraints - MUST / MUST NOT statements. Non-negotiable constraints specific to this directory. ## Guidance - SHOULD / SHOULD NOT statements. Recommendations that may be deviated from with justification. </context>Schema notes:
- The opening
<context>tag carries the relative path and a last updated date. - The description is prose, not a list. Answer "what is here" and "why does it exist."
- Summary covers every file and subdirectory. One line each.
- Constraints and Guidance are optional — only include them when the directory has rules worth stating. Use RFC-style language.
- Keep it short. This file will be read frequently by multiple agents.
- The opening
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.
- 2d ago First seen · 106 lines · 23 tokens per session scan A 31d56986f88d
context-maintenance is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,108 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.