A startup skill that makes the coding agent load and follow another matching skill before responding.

It is for enforcing skill selection and fallback rules at the beginning of agent conversations.

It helps ensure the agent uses the required project instructions instead of starting work without them.

using-dso — Skill for Claude Code by navapbc/digital-service-orchestra

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 navapbc/digital-service-orchestra --skill using-dso

Clone the repo

git clone --depth 1 https://github.com/navapbc/digital-service-orchestra

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/using-dso/github.svg)](https://agentmods.dev/skills/navapbc/digital-service-orchestra/using-dso)

Your own site

<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/using-dso"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/using-dso/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/using-dso"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/using-dso.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,339 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.

Model	Per session	Once invoked
Fable 5.1	$0.00123	$0.02339
Opus 5.5	$0.00049	$0.00936
Sonnet 5.5	$0.00025	$0.00468
Haiku 4.5	$0.00012	$0.00234

Measured 2mo ago against content hash e46401ce8e0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-dso 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 2mo 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.

plugins/dso/skills/using-dso/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to Access Skills

In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files unless the Skill tool's injection has silently failed (see below).

When the Skill tool returns Successfully loaded skill: The skill content should now be available in a <system-reminder> block in your context. Verify it is present by checking whether the skill's first section or phase instructions are visible. If skill instructions ARE visible, follow them directly — do NOT re-invoke the Skill tool or use the Read tool. If skill instructions are NOT visible in context (Skill tool succeeded but no content appeared), this is a silent injection failure — fall back immediately: read the skill file directly at skills/<skill-name>/SKILL.md (strip the dso: prefix to get the directory name) and follow its instructions. Do NOT re-invoke the Skill tool — re-invocation cannot fix a context injection failure and will loop indefinitely.

STOP — SILENT INJECTION FAILURE DETECTED: If the Skill tool returns only a brief terse string (e.g., "Launching skill: dso:sprint") with no follow-on content or instructions, YOU MUST immediately use the Read tool to load skills/<skill-name>/SKILL.md (strip the dso: prefix to get the directory name) and follow it. Do NOT respond to the user. Do NOT re-invoke the Skill tool. Do NOT ask a clarifying question. The fallback is mandatory and unconditional — execute it now.

If the Skill tool fails with "Unknown skill": Read the skill file directly at skills/<skill-name>/SKILL.md (strip the dso: prefix to get the directory name) and follow its instructions. Do NOT stop or report failure — the fallback is always available. This is a session-state issue (skill registry drift under long context), not a missing-skill problem.

Read the full file on GitHub · 154 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

HOOK-INJECTION.md 4.7 KB

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.

2mo ago First seen · 154 lines · 123 tokens per session scan A e46401ce8e0f

Subscribe to this mod's changes

using-dso is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 2,339 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.

Building agents

using-dso next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
using-dsonavapbc/digital-service-orchestra	Skill	6	yesterday	Apache-2.0	A	123	Claude Code
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	316k	7d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code