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/addit-digital/addit-harness/setupnpx skills add addit-digital/addit-harness --skill setupgit clone --depth 1 https://github.com/addit-digital/addit-harnessWhat 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 | $0.00075 | $0.01182 |
| Opus 5 | $0.00037 | $0.00591 |
| Sonnet 5 | $0.00015 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade B, and why
setup scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`./.claude/settings.json` — matches Claude Code's own memory-file How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
addit-harness setup
The addit-harness plugin ships agents/ and skills/ — those are already
live once the plugin is installed, nothing to do. This skill places the rest:
CLAUDE.md, AGENTS.md, rules/ (path-scoped language conventions),
references/, and settings.json — none of which Claude Code plugins can
carry natively (no plugin-level memory file, no path-scoped auto-load rules,
no plugin-carried permissions/model).
Choosing a scope — ask, don't silently default
--scope changes where files land in a way that's annoying to undo cleanly
(global touches every Claude Code session on the machine; project touches
just the current repo). Don't guess:
- If the user already passed
--scopeas an argument to this skill, use it as given — no need to ask. - If they didn't, and the conversation doesn't already make the intent
obvious (e.g. "just try it here" / "in this repo only" → project; "on my
machine" or no project context at all → global), ask which they want
before running anything. Offer
globalas the default recommendation since it matchesinstall.sh's existing behavior, but let them choose:global: places everything under~/.claude/— applies to every Claude Code session on the machine.project: placesCLAUDE.md,AGENTS.md,rules/,references/bare at the current project root, andsettings.jsonat./.claude/settings.json— matches Claude Code's own memory-file convention (project memory at root, project settings nested under.claude/) and only applies inside this one project.
- Mention while asking that the plugin itself can independently be scoped
too (
/plugin install addit-harness@addit --scope localkeeps agents/skills confined to this repo as well) — see the README's Install section for both mechanisms together.
What to run
Once the scope is settled, run the bundled script with the Bash tool:
bash "${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/setup.sh" --scope <global|project> [--link]
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.
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 · 89 lines · 75 tokens per session scan B 50b7fa7c382b
setup is a skill published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 1,182 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ccg-annotate
AI-driven annotation workflow for adding structured metadata to code. Annotations are indexed and searchable via FTS.
ccg-namespace
Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…
ccg-docs
Generate Markdown documentation from code graphs, build RAG indexes for AI consumption, and lint documentation quality.
ccg-analyze
Explicit-only deep analysis of algorithms, feature pipelines, and code relationships with CCG impact radius, bounded flow tracing, callers/callees, git-diff risk, affected stored flows, and cross-namespace references. Use only when the user explicitly names the ccg-analyze skill in the current request. Do not invoke…
ccg-build
Explicit-only graph ingestion for building, updating, migrating, and postprocessing code-context-graph graphs from source visible to the CCG runtime. Use only when the user explicitly names the ccg-build skill in the current request. Do not invoke merely because a graph is missing or stale, annotations need…
ccg
Fast read-only code discovery with a bounded code-context-graph search and targeted source verification. Use when an ordinary positive lookup or explanation needs an entry point, recorded intent, known-path inventory, or direct relationship evidence. Do not use for absence, completeness, exhaustive inventory, deep…