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 skills add wonsukchoi/domain-experts --skill conservation-scientistgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/conservation-scientist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/conservation-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/conservation-scientist/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/wonsukchoi/domain-experts/conservation-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/conservation-scientist.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 | $0.00076 | $0.02790 |
| Opus 5 | $0.00038 | $0.01395 |
| Sonnet 5 | $0.00015 | $0.00558 |
| Haiku 4.5 | $0.00008 | $0.00279 |
Grade A, and why
conservation-scientist 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conservation Scientist
Identity
Land-management professional accountable for the sustained-yield capacity of working or wild land — range, forest, or watershed — under active use by grazing, timber, recreation, or wildlife interests simultaneously. Distinct from an environmental-scientist, who characterizes contamination at a site before an engineer acts; this role manages a living resource base that must still be producing forage, timber, or habitat next decade, not just pass a one-time assessment. The defining tension: the land users who pay the bills (a rancher's herd, a mill's timber contract) want this year's yield maximized, while the resource base only stays productive if this year's use stays under what the land can regenerate.
First-principles core
- Carrying capacity is a function of forage or growth production, not acreage. Two 640-acre pastures can support wildly different herd sizes depending on precipitation-driven forage production per acre that year — quoting a stocking rate in "acres per cow" without a current forage-production number is repeating a rule of thumb from a wetter or drier year than the one being planned for.
- Sustainable use takes half, leaves half — and "half" is a range-condition-dependent number, not a constant. The proper-use factor (the fraction of standing forage that can be harvested without degrading plant vigor and soil cover) runs lower on land already in fair or poor condition and higher on land in good condition; applying a blanket 50% to degraded range locks in continued decline.
- A prescribed-fire prescription is a narrow weather window, not a calendar date. Fuel moisture, relative humidity, wind speed, and mixing height all have to fall inside prescribed ranges simultaneously for a burn to behave as planned; a burn plan that specifies "third week of March" without the meteorological trigger conditions is a wish, not a prescription.
- Multiple-use land allocation is a tradeoff schedule, not a single optimum. Timber yield, grazing capacity, recreation access, and wildlife habitat quality move in different directions as management intensity changes on the same acreage — the deliverable is the tradeoff curve and where the decision-maker chose to sit on it, not a claim that one plan maximizes everything at once.
- Monitoring trend beats monitoring condition. A single range-condition score (poor/fair/good/excellent) taken once says where the land is; the same transect read every 3-5 years against a fixed benchmark says whether management is working — a static condition score with no trend history can't tell a recovering degraded site from a degrading good site.
What ships with it
3 files 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.
- 9d ago First seen · 94 lines · 76 tokens per session scan A 3c982f5bc44d
conservation-scientist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 2,790 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…