chaincompiler
Orientation when working IN the chaincompiler repo — what the system is, where things live, and the discipline.
Skill by sancovp
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sancovp-chaincompiler
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/chaincompiler
What's inside
- Skill name
chaincompiler- Description
- Orientation when working IN the chaincompiler repo — what the system is, where things live, and the discipline. Use when developing or extending ChainCompiler, ACCC/CORCC/SCCC, chainaios, the persona compilers, goldenreq, glyphsteer, the SI, the marketplace, or the Skill OS.
- License
- MIT
- Instructions
- 54 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# ChainCompiler — repo orientation
A compiler-compiler for cognition: a **closed algebra over one type, the skill dir**
(`<name>/SKILL.md`). Every layer produces or consumes only that type.
**Read `DESIGN.md` first** — it is the design, one section per part; this skill is the map to it.
## Layout
```
DESIGN.md # the design — read it first
README · ROADMAP · BACKLOG · roadmap.json # public face + changelog · phases · tasks
FEDERATION · REBUILD-SPEC · DIETC-AIOS-REBUILD # reference detail (a plan and two records)
packages/ rulecatcher · honeyc · skillchain-compiler # the engine
chaincompiler # the base
accc · corcc · sccc # the chain tier
chainaios # the agent tier (installs the chaincompiler CLI)
personacc · personapack · goldenreq · glyphsteer · archetype · framework · si
skills/ · .mcp.json · .claude-plugin/ # the plugin payload
personas/ · examples/ · chains/ # worked agents · end-to-end examples · skillchain specs
assets/ · site/ · scripts/ · .github/ # generated roadmap + site, generators, workflows
.claude/rules/ # the tree law · the autoload fact · the diagrams · the mint flow
```
SkillTree is not in this repo: it is `agent-skilltree` on PyPI (import `skilltree`). `./install.sh`
installs every package editable plus the PyPI dependencies.
## The stack, bottom → top (`DESIGN.md` §2)
- **APE** (`agent-prompt-engineering`, PyPI) under everything — the prompt engine, the grammar seam, `write_skill`.
- **rulecatcher** (the gate) + **honeyc** (the compiler) = the engine.
- **chaincompiler** = the base: forge · gate · grammar · package · prime · the glyph-persona front end.
- **ACCC → CORCC → SCCC** = attention chains → chains of reasoning → skill chains (each emits a skill dir).
- **chainaios** = the agent tier: `construct_language`, `roll_up_algebra` (closure), `hierarchicalize`,
and the agent shapes GBA · COG · HBA (`DESIGN.md` §7–§8).
- Beside the tiers: **personacc/personapack** (personas), **goldenreq** (nothing promotes itself),
**glyphsteer** (retrieval steering), **archetype**, **framework** (the chapter rung), **si** (the
self-interpreter MCP).
Diagrams: `.claude/rules/21-architecture-diagrams.md` (the stack, the algebra, the package graph and every flow).
## Discipline (enforced)
When you finish a unit of work, in the SAME change: rewrite `DESIGN.md` where the design changed, tick
`BACKLOG.md`, update `roadmap.json` if a phase moved, add a `## Changelog` entry in `README.md`, and run
`python3 scripts/update_site.py`. The deploy gate fails the push without a new changelog entry. See
`.claude/rules/00-keeping-roadmap-and-backlog-current.md`; minting a chain follows
`.claude/rules/22-seq-mint-attention-chain.md`.
## Tests (`DESIGN.md` §19)
`./install.sh`, then `pytest packages`, `pytest examples/_all/test_all.py`,
`python examples/_all/bandit_self.py`, `pytest examples/nutrition`, `lint-imports`.From sancovp/chaincompiler, MIT.
More from sancovp/chaincompiler
- 0.458score
chainforge
sancovp
Chain-of-reasoning (spoken, ends in a decision) — a diagram is a formalized relationship structure, never decoration — never begin by drawing; determine what…
SkillAFreshness: AClaude Code +9 - 0.458score
bandit-chain-system
sancovp
How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit…
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer
sancovp
Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji/glyph vocabulary that biases search (lexical…
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer-dense
sancovp
Use when running GlyphSteer's DENSE regime — embedding-based emoji steering via the containerized ONNX sidecar.
SkillAFreshness: AClaude Code +9 - 0.458score
skilltree
sancovp
WHAT: turn a flat .claude/skills folder (or any folder of skills) into a walkable coordinate-addressed tree so the model loads one layer at a time instead of…
SkillAFreshness: AClaude Code +9 - 0.456score
boundary-keeper
sancovp
Chain-of-reasoning (spoken, ends in a decision) — a boundary defines inside, outside, interface, and crossing conditions — and abstraction layers stay stable…
SkillAFreshness: AClaude Code +9 - 0.456score
edge-typer
sancovp
Chain-of-reasoning (spoken, ends in a decision) — an arrow is not generic association, proximity is not causality, a container is not ownership — every…
SkillAFreshness: AClaude Code +9 - 0.456score
graph-auditor
sancovp
Chain-of-reasoning (spoken, ends in a decision) — an orphan node has no reason to exist, an ambiguous arrow is a lie, and invisible feedback is a hidden loop…
SkillAFreshness: AClaude Code +9 - 0.456score
diagram-compilation
sancovp
The master diagram-compilation AC — the whole walk from an unstructured concept to a validated legible diagram; each focus expands into its own sidechain…
SkillAFreshness: AClaude Code +9 - 0.455score
metaformal-self-test
sancovp
How to verify agent/COG/gate/AIOS behavior WITHOUT calling LLMs or writing tautology asserts — by triggering the real thing in the real substrate and…
SkillAFreshness: AClaude Code +9 - 0.454score
diagram-construction
sancovp
Skillchain — ac:diagram-compilation → ac:never-begin-by-drawing → cor:chainforge → Diagram-construction
SkillAFreshness: AClaude Code +9 - 0.452score
boundary-abstraction-pass
sancovp
The boundary pass — a system in, its explicit membrane out; membership is never implied, and nodes at incompatible abstraction levels never share a chain…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sancovp/chaincompiler
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sancovp
- 0.458score
bandit-chain-system
sancovp
How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit…
SkillAFreshness: AClaude Code +9 - 0.458score
chainforge
sancovp
Chain-of-reasoning (spoken, ends in a decision) — a diagram is a formalized relationship structure, never decoration — never begin by drawing; determine what…
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer-dense
sancovp
Use when running GlyphSteer's DENSE regime — embedding-based emoji steering via the containerized ONNX sidecar.
SkillAFreshness: AClaude Code +9 - 0.458score
skilltree
sancovp
WHAT: turn a flat .claude/skills folder (or any folder of skills) into a walkable coordinate-addressed tree so the model loads one layer at a time instead of…
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer
sancovp
Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji/glyph vocabulary that biases search (lexical…
SkillAFreshness: AClaude Code +9 - 0.456score
boundary-keeper
sancovp
Chain-of-reasoning (spoken, ends in a decision) — a boundary defines inside, outside, interface, and crossing conditions — and abstraction layers stay stable…
SkillAFreshness: AClaude Code +9
Cite this page
chaincompiler skill. Agent Mart. https://agentmart.dev/skills/sancovp-chaincompiler (last updated 2026-10-24)