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/devstride/claude-plugin/doctornpx skills add devstride/claude-plugin --skill doctorgit clone --depth 1 https://github.com/devstride/claude-pluginWhat 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 | $0.00033 | $0.05826 |
| Opus 5 | $0.00016 | $0.02913 |
| Sonnet 5 | $0.00007 | $0.01165 |
| Haiku 4.5 | $0.00003 | $0.00583 |
Grade A, and why
doctor 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 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.
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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human output. Read ${CLAUDE_PLUGIN_ROOT}/skills/build-item/references/plain-language-output.md once per top-level run; composed skills reuse it. Apply it to every message.
Diagnose whether this checkout can run the delivery loop and give exact repairs. Optional section:
env, plugin, devstride, config, ci, gates, or docs: $ARGUMENTS
With a repo root, run §4's status-line check on every invocation regardless of section; otherwise N/A.
Two-phase contract:
- Phase 1 is READ-ONLY. Inspect and report every requested check before fixing anything. Do not commit, checkout, write-fetch, push, create branches, change config, install/update, edit workflows, or call a DevStride write tool. Every "Fix:" below is text to print.
- Phase 2 starts only after the complete report and an explicit yes. First read
${CLAUDE_PLUGIN_ROOT}/skills/doctor/references/repairs.md; its eligibility tiers are fixed. Write only under this repo's.claude/, except the separately confirmed personal-status-line cleanup inrepairs.md; never repair workflows, git state, DevStride records, or stages.
How to report
Human recap. Walk every requested section after failures. For each result say PASS,
FAIL, or N/A, then Found: in plain words. A failure adds Why it matters: and Fix:
with the exact command or edit. After any repair add Changed: and Result:. Never pass an unrun
check. End ready, ready-with-warnings (name them), or not-ready (name blockers), plus one
next action. For each failure symptom, read
${CLAUDE_PLUGIN_ROOT}/skills/doctor/references/silent-failures.md (also the rationale for §4–§6).
1. Environment (env)
- git —
git --version; confirm you are inside a repo (git rev-parse --is-inside-work-tree). Not a repo → the rest is N/A; say so and stop the section. - An
originremote —git remote get-url origin, checked by name because delivery skills hardcode it. Other remotes but noorigin→ say which. - gh present —
gh --version. Missing → the whole delivery half is unavailable: no pull requests, no review threads, no ready-flip. Fix: install GitHub CLI (brew install gh, or cli.github.com). - gh authenticated —
gh auth status. Fix:gh auth login. - gh scopes, for the ACTIVE account — read the account marked active (
gh auth statuscan list several). Minimumrepo+read:org, plusworkflowif the loop edits workflow files. Fix:gh auth refresh -s repo,read:org— includingworkflowin the SAME list when that is the missing scope. Auth fromGH_TOKEN/GITHUB_TOKEN→ say so:refreshcannot touch an environment token; unset it or reissue with the scopes. - Forge — non-GitHub
origin: delivery assumes GitHub/Actions; planning still works.
What ships with it
4 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.
- 2d ago First seen · 326 lines · 33 tokens per session scan A d3b4a154983c
doctor is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 5,826 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
dsh-ci-test-reliability
Design, review, and diagnose DeepSeek Harness tests and fixtures that can fail nondeterministically under CI concurrency, shared host resources, clocks, process-global state, subprocesses, network listeners, or asynchronous teardown. Use when adding or changing tests with those risks, investigating flaky CI, or…
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
dsh-web-pre-push-checks
Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…