ssot-navigation
Skill0 starsChanged 57 days agoApache-2.0View on GitHub
Use when starting any task to determine which arbiter SSOT documents to read and in what order.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- architect-reviewSkill
- brainstormingSkill
- clean-codeSkill
- close-gold-gapSkill
- codebase-auditSkill
- configureSkill
- context-rot-managementSkill
- epic-decomposeSkill
- gold-auditSkill
- impactSkill
- levelupSkill
- product-acceptanceSkill
- refutationSkill
- senior-surveySkill
- tabletopSkill
- tddSkill
- understand-codeSkill
- verificationSkill
- visual-verificationSkill
- wave-drainSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
When documents conflict, higher level wins.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SSOT Navigation
Decision Hierarchy
When documents conflict, higher level wins.
| Level | Authority | Path |
| 1 | Invariants + governance contract | AGENTS.md |
| 2 | Architecture decision records | docs/internal/ADR/ |
| 3 | Process rules | docs/internal/SYSTEM/CANON.md |
| 4 | Active task plan | .claude/plans/<task>.md |
| 5 | AI judgment | (last resort) |
SSOT Document Index
| Document | Path | Purpose | When to read |
| Governance contract | AGENTS.md | Invariants, authority hierarchy, tool config | Every task, first |
| Process rules | docs/internal/SYSTEM/CANON.md | 15 CANON-NN constraints from audit waves | Before adding hook/gate/template/command |
| Decision records | docs/internal/ADR/ | Architectural decisions with rationale | Before changing existing abstractions |
| Doc index | docs/INDEX.md | Generated index of all docs + the wiki | When orientation is slow |
| SSOT core set | docs/internal/METHOD/SSOT_CORE_SET.md | Minimal reading list per task type | When uncertain which docs apply |
| Invariant catalog | src/invariants/catalog.ts | Machine-readable INV-NN entries | Before adding a new invariant |
| Generated invariants | GLOBAL_INVARIANTS.md | Rendered output for target projects | To verify filter/render pipeline |
| Decisions log | docs/internal/SYSTEM/DECISIONS.md | Running ADR index | Before changing architectural scope |
Key Line-Range Pointers
| Reference | Location |
| Authority Hierarchy | AGENTS.md §Authority Hierarchy L22-32 |
| Invariant list | AGENTS.md §Invariants L34+ |
| How to add an invariant | docs/internal/SYSTEM/CANON.md §How to add new entry L21+ |
| Filter short-circuit | src/invariants/filter.ts:23-37 |
| Task evidence path | src/commands/task.ts:194-208 |
Quick Lookup Commands
# Find where an invariant is cited
grep -n "INV-NN" AGENTS.md
# List issues tagged with a CANON rule
gh issue list --label "canon/NN-*"
# Explain an invariant in human language
arbiter explain INV-NN
# List all active invariants and error codes, grouped by category
arbiter explain --listAnti-Patterns
- Starting implementation without reading
AGENTS.md §Invariants— risks INV violation on first edit - Assuming an ADR exists without opening
docs/internal/ADR/— ADRs are sparse; verify before citing - Adding a hook, gate, or template without checking CANON before CANON-01/04/07/10/11/15
- Editing
AGENTS.mdwithoutARBITER_SSOT_BYPASS=1—pre-edit-ssot-guard.mjshard-blocks
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

