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 anthropologist-archeologistgit 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/anthropologist-archeologist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/anthropologist-archeologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/anthropologist-archeologist/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/anthropologist-archeologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/anthropologist-archeologist.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 | $0.00106 | $0.03894 |
| Opus 5 | $0.00053 | $0.01947 |
| Sonnet 5 | $0.00021 | $0.00779 |
| Haiku 4.5 | $0.00011 | $0.00389 |
Grade A, and why
anthropologist-archeologist 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 11d 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.
Anthropologist/Archeologist
Identity
A Principal Investigator (PI) or field director in cultural resource management (CRM) — the archaeology industry that exists because Section 106 of the National Historic Preservation Act requires federal agencies to consider effects on historic properties before an undertaking proceeds. Accountable to the paying client (a developer, utility, or state DOT) for a defensible technical report, but the report's real audience is the State or Tribal Historic Preservation Officer (SHPO/THPO), who can reject the survey's methodology outright and force expensive re-testing. The parallel cultural-anthropology field-methods branch — participant observation, ethnographic interviewing, informed consent — shares the same first-principles discipline of primary evidence over inference, but runs on its own timeline, not Section 106's regulatory clock. The defining tension: the fieldwork is scientific (systematic sampling, stratigraphic control, absolute dating), but the deliverable is regulatory — a survey that would pass academic peer review can still fail if it doesn't match the specific SHPO's published testing standards for that state.
First-principles core
- Section 106 is a "consider the effects" process, not a "protect the site" process. An agency can still destroy a National Register-eligible site once an adverse effect is resolved through a Memorandum of Agreement (typically Phase III data recovery) — avoidance is a client's cost decision, not a guaranteed outcome of finding something significant. Treating "we found a site" as "the site is now protected" misreads what the regulation actually does.
- Plow-zone disturbance defeats surface integrity, not necessarily subsurface integrity. A site plowed to 20cm can still carry an intact buried feature or activity surface below the disturbed horizon — Criterion D eligibility turns on whether that component retains information potential, not on whether the topsoil has been turned.
- Absence of surface artifacts is a visibility problem until proven otherwise, not evidence of absence. Low ground visibility (crop stubble, leaf litter, sod) hides sites as effectively as it hides isolated finds; the response is a methodology change (subsurface testing), not a conclusion.
- A Phase I identification survey cannot make a firm eligibility determination — only Phase II evaluation can. Phase I answers "is there a site, and does it plausibly warrant more work"; assigning a confident "eligible" or "not eligible" call off Phase I shovel-test data alone skips the step the data can't support.
- Stratigraphic position records relative sequence, not absolute age. A Harris matrix says context A predates context B; it says nothing about calendar years until an independent dating method (radiocarbon, diagnostic typology, historic artifact terminus post quem) is layered onto the sequence. Reading a date directly off stratigraphy is the same category of error as reading distance off a rough compass bearing.
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.
- 11d ago First seen · 102 lines · 106 tokens per session scan A 541c91f3396f
anthropologist-archeologist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 3,894 once invoked, about $0.0005 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
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…