succinctly: Skill for Claude Code

.claude/skills/yaml-semi-indexing/SKILL.md

yaml-semi-indexing is a skill for Claude Code from rust-works/succinctly. It costs 60 tokens per session (2,232 once invoked), scanned A, original, MIT.

Technical guidance for YAML semi-indexing, a compact structure used to navigate YAML data efficiently. YAML is a human-readable data format often used for configuration files.

In plain words
What is it for?
Use it when implementing or debugging a YAML parser, semi-index, or cursor navigation, especially for block sequences, multi-line sequence items, and tree structure indexes.
Why use it?
It explains the special cases that make YAML navigation different from simpler formats such as JSON, including nested sequences and mappings. This helps avoid incorrect cursor positions and type lookups.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is rust-works/succinctly's own configuration. It tells Claude Code how to work on succinctly itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything succinctly configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rust-works/succinctly. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rust-works/succinctly/main/.claude/skills/yaml-semi-indexing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rust-works/succinctly

Made for: Claude Code.

Wrote 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.

agentmods badge for yaml-semi-indexing

README.md
[![agentmods](https://agentmods.dev/badge/skills/rust-works/succinctly/yaml-semi-indexing/github.svg)](https://agentmods.dev/skills/rust-works/succinctly/yaml-semi-indexing)
Your own site
<a href="https://agentmods.dev/skills/rust-works/succinctly/yaml-semi-indexing"><img src="https://agentmods.dev/badge/skills/rust-works/succinctly/yaml-semi-indexing/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.

agentmods 80×15 button for yaml-semi-indexing

Your own site · 80×15
<a href="https://agentmods.dev/skills/rust-works/succinctly/yaml-semi-indexing"><img src="https://agentmods.dev/badge/skills/rust-works/succinctly/yaml-semi-indexing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.02232
Opus 5.5 $0.00024 $0.00893
Sonnet 5.5 $0.00012 $0.00446
Haiku 4.5 $0.00006 $0.00223

Measured 2mo ago against content hash f8ecd89f6a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yaml-semi-indexing 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 2mo 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.

.claude/skills/yaml-semi-indexing/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YAML Semi-Indexing Skill

Implementation details for YAML semi-indexing using succinct data structures.

Comprehensive documentation: See docs/parsing/yaml.md for full parsing architecture.

Semi-Index Structure

YAML uses more components than JSON due to its richer structure:

  • Interest Bits (IB): Marks structural positions (keys, values, items)
  • Balanced Parentheses (BP): Encodes tree structure for navigation
  • Type Bits (TY): Distinguishes mappings (0) from sequences (1)
  • Sequence Item Bits (seq_items): Marks BP positions that are sequence item wrappers

Key Insight: Sequence Items vs Containers

Sequence items have BP open/close pairs but NO TY entry. This affects TY index calculations:

// WRONG: Direct rank gives incorrect TY index when seq_items exist
let ty_idx = bp.rank1(bp_pos);

// CORRECT: Subtract sequence items to get real container index
let bp_opens_before = bp.rank1(bp_pos);
let seq_items_before = count_seq_items_before(bp_pos);
let ty_idx = bp_opens_before.saturating_sub(seq_items_before);

Block Sequence Parsing

Multi-line Sequence Items

For YAML like:

-
  name: Mark
  hr: 65

The sequence item must remain open so content on subsequent lines becomes the item's value:

  1. Parse - at indent 0 → open sequence, open item, push (indent+1, SequenceItem) to stacks
  2. at_line_end() is true → return (item stays open)
  3. Next line name: Mark at indent 2 → parse_mapping_entry(2)
  4. Mapping opened inside the still-open item
  5. Subsequent lines at same indent add to mapping
  6. When indent returns to 0, close_deeper_indents closes mapping, item, etc.

Inline Compact Mappings

For - name: Mark\n hr: 65:

  1. Parse - → open sequence, open item
  2. looks_like_mapping_entry() is true → call parse_compact_mapping_entry(indent+2)
  3. Mapping opened but NOT closed after first entry
  4. Item also NOT closed
  5. Next line hr: 65 at indent 2 adds to the same mapping

Read the full file on GitHub · 214 lines

Changes

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.

  1. 2mo ago First seen · 214 lines · 60 tokens per session scan A f8ecd89f6a42

Subscribe to this mod's changes

yaml-semi-indexing is a skill published in the GitHub repository rust-works/succinctly (52 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 2,232 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 2026-08-30.

Related

yaml-semi-indexing compared with skills from other repositories

yaml-semi-indexing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
yaml-semi-indexingrust-works/succinctlySkill52yesterdayMITA60Claude Code
systematic-debuggingopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7k3d agoMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill319yesterdayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skillsSkill1.9k23d agoMITA36Claude Code
triaging-web-analytics-supportPostHog/posthogSkill41kyesterdaynoneA151Claude Code, Codex