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 DmitriyYukhanov/claude-plugins --skill analyzegit clone --depth 1 https://github.com/DmitriyYukhanov/claude-pluginsWrote 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/dmitriyyukhanov/claude-plugins/analyze)<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/analyze"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/analyze.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.01189 |
| Opus 5 | $0.00049 | $0.00594 |
| Sonnet 5 | $0.00020 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
analyze 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze — Tour Spec Authoring
Read input artifact(s) and write a tour-spec.json that the renderer consumes. Hand off to learning-guide:render at the end.
Trigger phrases
- "create a learning guide for X"
- "make an interactive tour"
- "generate onboarding doc"
- "build a learning module from this session"
Inputs to collect from the user
- Source artifact path(s) — required. One or more files/folders.
- Output directory — default
<input-parent>/learning/. - Archetype hint — optional; auto-detect with these rules:
- Filename ends
.observations.mdOR YAML frontmatter containssession_date:→planning-session. - Input is a directory of source files with no obvious doc layer →
codebase. - Input contains "Phase 1", "Phase 2", "rollout", "blockers" structure →
refactor-plan. - Otherwise →
generic.
- Filename ends
- Language — auto-detect from input text dominance; require >80% single-locale tokens to commit, otherwise default
en. Always state the detected language and offer an override before drafting.
Flow
- Resolve inputs. Confirm path(s) and output dir before reading anything large. Reject non-existent paths.
- Pick archetype. Auto-detect, state the choice, ask the user to confirm or override.
- Load archetype reference. Read
references/archetype-<name>.md. - Survey the input.
- Codebase: structured exploration — entry points, module map, control flow.
- Doc: top-to-bottom read.
- Session: lift decisions, blockers, files-touched.
- Discover embedded sources. Look for user-authored markdown referenced from the input (links, frontmatter
artifacts:lists, sibling.mdfiles). If none found AND archetype iscodebaseorgeneric, plan to synthesizetour-companion.mdperreferences/synthesis-contract.md. - Discover external link tokens. Scan input for ticket/issue patterns. Ask the user for URL templates (e.g.,
TICKET-→https://tracker.example.com/browse/TICKET-{id}). Templates must start withhttp://,https://, ormailto:and contain{id}— the renderer rejects other schemes. - Discover cross-ref patterns. Per
references/cross-ref-design.md. Propose only token-shaped patterns; bare words are forbidden. Show the user the proposed list, get confirmation. - Draft the tour spec. Follow the archetype's section outline. Each section gets a markdown body, optional inline quiz. Synthesize
tour-companion.mdif planned in step 5. Usereferences/spec-authoring.mdforbody_mdstyle. - Quality gates. Before handoff, verify:
- Every section has non-empty
body_md. - Every section with
level >= 2has aparent(the renderer rejects a spec that violates this — the JSON Schema only hints it for editors). - Every cross-ref pattern uses a non-bare-word token shape, names an existing source, AND its
anchor_formatresolves to a heading in that source. Heading anchors are bare slugs with nosection-prefix (seereferences/cross-ref-design.md). - Every
external_linkstemplate starts with an allowed scheme (http(s):///mailto:) and contains{id}. - Every quiz
answer_indexis in[0, options.length-1]. - Mermaid blocks parse as valid (best-effort regex on the first non-blank line).
- Every section has non-empty
- Hand off to render. Invoke
learning-guide:renderwith the spec path. No "shall I render?" gate — render is cheap and idempotent.
What ships with it
7 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.
- 7d ago First seen · 66 lines · 98 tokens per session scan A 5336ad062743
analyze is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,189 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 2026-08-31.
Other skills, from other repositories
explain
Comprehensive deep-dive explanation of GitHub repos, live websites/products, competitors, data products, algorithms/calculators, concepts, or any topic. Spawns parallel research + exploration agents, drives a real browser for live products, reverse-engineers calculators to runnable validated code, and saves a full doc…
quiz-me
Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…
code-standards
Prabhdeep (Sonu) Singh's personal coding standards — the house rules and quality bar for how code gets written. INVOKE before writing, generating, refactoring, or reviewing ANY code in ANY language — schemas, endpoints, queries, logging, validation, error handling — even when nobody says "standards" or "style".…
ticket-lifecycle
The ticket-as-control-plane rulebook — the single home for the tracker-operations contract, tracker resolution, the type/priority taxonomy, human-only trigger authorization, derived status, and trust boundaries. INVOKE when reading or writing tickets in a queue-driven flow, resolving a repo's tracker, or deciding…
self-review
Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, parallel review lenses with adversarial synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points attention …
design-tree
Make design decisions as an explicit branching tree — genuine alternatives, decisive rationale, rejected branches preserved. INVOKE PROACTIVELY when planning or designing any implementation approach, or choosing between architectures, libraries, or data models — especially in plan mode. Skip trivial or forced changes…