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/nikiforovall/claude-code-rules/reflect-treenpx skills add NikiforovAll/claude-code-rules --skill reflect-treegit clone --depth 1 https://github.com/NikiforovAll/claude-code-rulesWrote 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/nikiforovall/claude-code-rules/reflect-tree)<a href="https://agentmods.dev/skills/nikiforovall/claude-code-rules/reflect-tree"><img src="https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/reflect-tree.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 | $0.00115 | $0.02660 |
| Opus 5 | $0.00057 | $0.01330 |
| Sonnet 5 | $0.00023 | $0.00532 |
| Haiku 4.5 | $0.00012 | $0.00266 |
Grade A, and why
reflect-tree 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 4d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reflect-tree — session quest-tree
Produce a single-file interactive HTML quest-tree of a Claude Code session. The vertical spine is the linear sequence of turns; back-edges and off-spine nodes encode wrong turns (corrections, retries, reversals, dead-ends, backtracks) so the user can see the whole journey at a glance — including detours and where the agent had to redo work.
This is a sibling to /reflect. Same input contract, different output: /reflect is a two-pane incidents/recommendations dashboard; /reflect-tree is a graph.
When to use
- User invokes
/reflect-tree(no args) → analyze the current session from the in-context conversation. Do not re-read the session JSONL — work from the agent's own memory. - User invokes
/reflect-tree <session-id>or/reflect-tree <path-to-jsonl>→ runscripts/analyze_session.py <path>directly (this skill runs in a forked context —context: fork— so the compressed transcript is safe to ingest). The script outputs a compact markdown transcript: system reminders stripped, tool calls/results collapsed to one-liners, compaction blocks expanded with embedded user quotes. Then you classify each turn — the script does NOT classify, it only compresses.
Session JSONLs live under: ~/.claude/projects/<encoded-cwd>/<session-id>.jsonl
Node classifications
Each turn becomes a node. Pick the strongest applicable label:
- normal — routine forward progress (user request or assistant tool call/result with no problem)
- correction — user pushed back on an approach (
"no","don't","stop","actually") - retry — agent ran the same tool/intent 2+ times with variations before it worked
- reversal — agent edited then unwound (Edit → revert, Write → delete)
- dead-end — tool failed because of the environment (missing binary, wrong path, OS mismatch)
- backtrack — agent abandoned a path and resumed from an earlier state
- self-correction — agent caught its own mistake mid-stream
What ships with it
2 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.
- 4d ago First seen · 150 lines · 0 tokens per session scan A 862fb2e195b1
reflect-tree is a skill published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 5d ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,660 once invoked, about $0.0006 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
review-pr
Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…
researcher
Use when asked to create research documents, generate PDFs, make one-pagers, or create cheatsheets. Triggers: "research document", "generate PDF", "one-pager", "cheatsheet", "distinctive design". Provides HTML/Markdown/PDF with Terminal, Editorial, Corporate, Industrial, Fresh aesthetic presets.
start-thread
Use when opening OR RESUMING a unit of work — a feature, bug, research spike, refactor, an experiment — that should survive context loss in its own scratch workspace with a handoff doc. Idempotent create-or-resume: a fresh topic gets a scaffolded STATE doc; an existing thread gets a resume briefing (STATE + live…
save-state
Use when you need the whole picture of active work in this project — at session start, after a context clear or /compact, when finishing a work item, or when asked "what's in flight", "what am I building", "show the overall picture", or "save state".
infrastructure-planning
Plan and document the required software, infrastructure, and logistics for a Paperclip company — domains, GitHub, Docker Hub, Kubernetes, Slack, Google Workspace, Stripe, shipping providers, and CI/CD pipelines. Use when setting up infrastructure for a new company or auditing what an existing company needs.
work-planning
Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces .planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals…