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 KalarisLabs/Skill-Doctor --skill project-contextgit clone --depth 1 https://github.com/KalarisLabs/Skill-DoctorWrote 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/kalarislabs/skill-doctor/project-context)<a href="https://agentmods.dev/skills/kalarislabs/skill-doctor/project-context"><img src="https://agentmods.dev/badge/skills/kalarislabs/skill-doctor/project-context/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/kalarislabs/skill-doctor/project-context"><img src="https://agentmods.dev/badge/skills/kalarislabs/skill-doctor/project-context.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 | $0.00041 | $0.00634 |
| Opus 5.5 | $0.00016 | $0.00254 |
| Sonnet 5.5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
project-context 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project context
Read AGENTS.md then CONTEXT.md if they exist. This skill is the short form.
Product
Skill Doctor is a Rust CLI that scans AI agent skill files. The shippable core is deterministic L1. L2 (host-delegated semantics), L3 (sandbox), and L4 (intel) are optional and must degrade to reduced coverage, never a crash or a dropped L1 finding.
Repo: KalarisLabs/Skill-Doctor. Do not create a new GitHub repository.
Pipeline
input → L0 intake/digest/cache
→ L1 static engines THE PRODUCT
→ L2 host-delegated MCP optional, additive-only
→ L3 process harness + replay feature sandbox
→ L4 threat intel network opt-in
→ L5 score / coverage / report
Default CLI: L0+L1+L5 with --offline --deterministic.
Crate map
| Crate | Owns |
|---|---|
skill-doctor |
clap, printers, exit codes |
skill-doctor-core |
L0/L1/L4/L5, taxonomy, scoring |
skill-doctor-rules |
build.rs compiles rules/ |
skill-doctor-neutralize |
SD-11 envelope, no I/O |
skill-doctor-mcp |
host-delegated MCP |
skill-doctor-sandbox |
L3, only crate that may use unsafe |
SDTM-v1 — do not renumber
SD-01 prompt injection · SD-02 command injection · SD-03 exfil · SD-04 scope (capability differ, no model) · SD-05 supply chain · SD-06 SSRF · SD-07 tool poisoning · SD-08 backdoors · SD-09 flooding · SD-10 obfuscation · SD-11 scanner-mediated injection.
Exit codes (stable)
0 clean · 1 usage/internal · 2 findings ≥ --fail-on · 3 coverage under threshold.
Build order if the tree is still a stub
- CLI
--help/version/scanstub - L0 digest
- rules crate + one YARA rule per class
- L1 engines
- L5 reports + exit codes
- additive-only scorer + neutralize
- fixtures + determinism test
- MCP
- CI matching
TESTING.md - release last
Load rust-invariants before changing defaults. Load ci-cd before touching workflows. Load rust-perf before optimizing.
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.
- 1mo ago First seen · 62 lines · 41 tokens per session scan A 002a05297062
project-context is a skill published in the GitHub repository KalarisLabs/Skill-Doctor (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 634 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.