Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/quick-ref)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/quick-ref"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/quick-ref/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/navapbc/digital-service-orchestra/quick-ref"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/quick-ref.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 | $0.00126 | $0.00746 |
| Opus 5.5 | $0.00050 | $0.00298 |
| Sonnet 5.5 | $0.00025 | $0.00149 |
| Haiku 4.5 | $0.00013 | $0.00075 |
Grade A, and why
quick-ref scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Reference: Plugin Scripts & Skills
Auto-discovers all available scripts and skills in the workflow plugin at invocation time. No hardcoded lists — everything is resolved dynamically.
Usage
/dso:quick-ref # Show all scripts and skills
/dso:quick-ref scripts # Show only scripts
/dso:quick-ref skills # Show only skills
Execution
Step 1: Resolve Plugin Root
REPO_ROOT="$(git rev-parse --show-toplevel)"
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
Step 2: Discover Plugin Scripts
List all .sh files in the plugin scripts/ directory and extract the first comment line (after the shebang and filename comment) as a description.
scripts_dir="${PLUGIN_ROOT}/scripts"
for script in "$scripts_dir"/*.sh; do
name="$(basename "$script")"
# Extract the description: second comment line (first after #!/... line)
desc="$(sed -n '2s/^# *//p' "$script")"
# If line 2 is a filename echo, try line 3
if [[ "$desc" == *"$name"* ]] || [[ -z "$desc" ]]; then
desc="$(sed -n '3s/^# *//p' "$script")"
fi
echo "| $name | $desc |"
done
Present the results as a markdown table:
| Script | Description |
|---|---|
| (auto-discovered at invocation time) | (first comment line) |
Step 3: Discover Skills
List all skills by scanning for SKILL.md files under the plugin skills/ directory.
skills_dir="${PLUGIN_ROOT}/skills"
for skill_file in "$skills_dir"/*/SKILL.md; do
skill_dir="$(dirname "$skill_file")"
skill_name="$(basename "$skill_dir")"
# Extract description from YAML frontmatter
desc="$(sed -n '/^description:/s/^description: *//p' "$skill_file")"
# Check if user-invocable
invocable="$(sed -n '/^user-invocable:/s/^user-invocable: *//p' "$skill_file")"
echo "| /$skill_name | $desc | $invocable |"
done
Present the results as a markdown table:
| Skill | Description | User-Invocable |
|---|---|---|
| (auto-discovered at invocation time) | (from frontmatter) | (true/false) |
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 · 79 lines · 126 tokens per session scan A 4b6b5b41c26b
quick-ref is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 126 tokens to every session and 746 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.
quick-ref compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quick-refnavapbc/digital-service-orchestra | Skill | 6 | yesterday | Apache-2.0 | A | 126 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 113k | today | MIT | A | 30 | Claude Code, Codex |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 6d ago | MIT | A | 184 | Claude Code |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | today | MIT | A | 52 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 3d ago | MIT | A | 33 | Claude Code, Codex |