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 dgilford/ai-science-toolkit/plugin install ai-science-toolkitWrote 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/dgilford/ai-science-toolkit/repo-init)<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/repo-init"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/repo-init/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/dgilford/ai-science-toolkit/repo-init"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/repo-init.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 | $0.00067 | $0.02829 |
| Opus 5 | $0.00034 | $0.01414 |
| Sonnet 5 | $0.00013 | $0.00566 |
| Haiku 4.5 | $0.00007 | $0.00283 |
Grade A, and why
repo-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize a repository with a standard, opinionated project structure. Run once per project. Re-running (or running on an existing repo) adds missing pieces only — it never overwrites or repairs existing files.
The intake is a hard gate. Create nothing — no directories, no files, not even git init — until the step-2 intake is either completed with the user or skipped by an explicit flag (--no-grill / --dry-run). Scaffolding first and asking later defeats the skill: the answers determine what gets scaffolded.
File templates (loaded at runtime)
D="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/repo-init}"; D="${D:-$HOME/.claude/skills/repo-init}"; cat "$D/TEMPLATES.md" 2>/dev/null || echo "(TEMPLATES.md not found — abort and report a broken install)"
Live state
pwd && git rev-parse --show-toplevel 2>/dev/null || echo "(not a git repo yet)"
Modes
| Invocation | Mode | Shape |
|---|---|---|
/repo-init |
research (default) | Analysis project: notebooks, script-first compute, gitignored data/figures |
/repo-init --package |
package | Distributable library: src-layout, pyproject, tests, CI, CITATION.cff |
[path] |
either | Target directory (default: cwd). Must exist or be creatable. |
--no-license |
either | Skip the LICENSE file and the pyproject/CITATION license fields. |
--no-grill |
either | Skip the intake grill; scaffold with template stubs as-is (LICENSE defaults to MIT with the git author as holder — flagged in the report). |
--dry-run |
either | Print the would-be report (every path → created/skipped) for the flag-resolved mode, without writing anything, running git init, or grilling. (Since the grill is skipped, decisions it would set — mode flip, license, data guards — are not previewed.) |
Ground rules
- Never destructive. Before writing any file: if it already exists, skip it — never overwrite, never merge silently.
mkdir -pfor directories is always fine. Reportskipped (exists); reserveskipped (exists — differs from template)for files that look like a broken or partial scaffold (unfilled placeholders, a template skeleton with no real content). Pre-existing real content is normal, not a warning. - Two sanctioned exceptions to "never touch an existing file":
.gitignore— never rewrite; diff it against the template entries, report which standard entries are missing, and ask before appending (gitignoring is a deliberate choice). After any append, rungit ls-filesagainst the newly ignored patterns: if matches exist, warn explicitly that.gitignoredoes not untrack already-committed files (they stay in the repo and its history untilgit rm --cached/ a history rewrite) — this matters most before a repo ever goes public.docs/DECISIONS.md— an append-only ledger: a re-run appends a new dated init entry recording that run's intake answers; existing entries are never edited or rewritten.
- CLAUDE.md / AGENTS.md on retrofit: if
CLAUDE.mdalready exists and is not the redirect stub (compare against the CLAUDE-STUB template), do not createAGENTS.md— ask the user: keepCLAUDE.mdcanonical (scaffold no AGENTS.md, or an inverted 3-line AGENTS.md stub pointing at CLAUDE.md), or migrate to the AGENTS-canonical pattern. Never leave both files substantive — that split-brain is exactly what the redirect convention exists to prevent. - Substitute all
{{PLACEHOLDERS}}and<angle-bracket>fills per the header of TEMPLATES.md before writing.{{AUTHOR}}/{{EMAIL}}come fromgit config user.name/user.email; if unset, use a<fill me in>placeholder and flag it in the report. If the intake changes the mode, redo step-1 resolution (including{{PKG_NAME}}) before scaffolding.
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.
- 12d ago First seen · 102 lines · 67 tokens per session scan A 5f4339f10b6f
repo-init is a skill published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 23d ago), licensed MIT. It adds 67 tokens to every session and 2,829 once invoked, about $0.0003 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.
Other skills, from other repositories
metforge-model-diagnose
Diagnose atmospheric-model and dynamical-core experiments. Use for idealized tests, balanced flow, hydrostatic rest, density currents, advection, gravity/acoustic waves, mountain waves, baroclinic instability, conservation and budget closure, error growth, convergence, timestep/resolution/domain/MPI sensitivity…
metforge-analysis
Perform reproducible atmospheric-science calculations and statistical diagnostics. Use when the agent needs to calculate established or custom climate indices, derive meteorological variables, compute trends, detrend or filter time series, perform EOF/PCA, regression, correlation, composites, bootstrap or significance…
metforge-data
Acquire and prepare atmospheric, climate, and Earth-system datasets reproducibly. Use when the agent needs to find an authoritative dataset, choose among ERA5/CMIP/GPM/MERRA-2/NOAA or similar products, download or subset NetCDF/GRIB/Zarr data, write CDS/Earthdata/ESGF/OPeNDAP acquisition code, inspect coordinates and…
metforge-figure
Design, create, revise, and audit atmospheric-science figures. Use for maps, map differences, vertical sections, Hovmöller diagrams, profiles, spectra, budgets, convergence plots, conservation/error-growth diagnostics, ensemble comparisons, and publication multi-panel figures from NetCDF/xarray or tabular data. Also…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-rust
This is a Hermes-native rust workflow skill.