fix(aidd-context): source-backed tool references, with dates and unverified cells

[alexsoyes]

Problem

plugins/aidd-context/skills/08-hook-generate/references/tool-paths.md stated that Codex CLI has no session-end moment. Codex documents SessionEnd explicitly. The claim was wrong, and it propagated: a downstream design decision was taken on it before anyone re-read the source.

The failure is structural, not a typo. Not one cell in that table carried a URL or a date. Nothing distinguished "read in the docs" from "assumed in 2026-06 and never re-checked", so the only way to audit one cell was to re-verify all of them. A reference that cannot be audited cell by cell decays silently, and agents quote it with full confidence.

These references are load-bearing: a skill reads them instead of the vendor docs, so an error there becomes an error in every artefact the skill generates.

Scope

Applies to reference files that make per-tool factual claims, starting with 08-hook-generate/references/tool-paths.md.

• Per-claim verification marks. [v] = read in the official docs on the stated date. [?] = not re-read, unverified. An unverified cell stays unverified; it is never filled with a plausible value.
• Sources section. Every page actually read, with its URL, plus the date of the pass. Redirects noted with their target (developers.openai.com/codex/hooks and docs.github.com/.../hooks-configuration both moved).
• Re-verification trigger. State when a [v] becomes stale and must be re-read.
• Extend to the other per-tool references in aidd-context once the shape is agreed (11-explore/references/ai-mapping.md, 03-context-generate/references/ai-mapping.md).

A first pass over tool-paths.md is written and ready to land with this issue: marks, sources, verification date, plus the corrections below.

Corrections found while verifying (5 tools, official docs, 2026-08-11)

• Codex has SessionEnd. Previously recorded as absent. Timeout is 1 s by default, 3 s max, and it does not run for subagents.
• Copilot casing is not an alias. The configured casing selects the payload format (camelCase fields vs snake_case) and sometimes the event name itself: agentStop becomes Stop, userPromptSubmitted becomes UserPromptSubmit. The file described it as accepting both names.
• Failure semantics differ per tool, and one denies. A preToolUse handler that exits non-zero on Copilot denies the tool call. An observer hook that throws stops the agent. Not documented anywhere in the file before.
• OpenCode confirmed as plugins-only, with no session-end event and no session identifier in the plugin context.
• Session identifier field names differ across all four supported tools (session_id, conversation_id, sessionId) and none of the five documents whether the value survives a resume, clear, compaction or fork.

Acceptance criteria

• Every factual cell in tool-paths.md carries [v] or [?].
• A Sources section lists each page read, with the date of the pass.
• The five corrections above are reflected in the file.
• A [?] cell is never silently promoted to [v] without a re-read.
• The shape is agreed before extending to the other reference files.

Prior art in this repo

• plugins/aidd-context/skills/08-hook-generate/references/tool-paths.md — the file this issue fixes.
• plugins/aidd-context/skills/08-hook-generate/references/hook-authoring.md — R1-R7, which delegate every per-tool fact to tool-paths.md.
• AGENTS.md — "Don't guess APIs, signatures, flags, or behavior" and "Don't assume your knowledge is current" already carry the intent. This issue does not add a rule; it makes the existing ones auditable in the file that holds the claims.

Relations

Field	Value
related	#617

Verified against: Claude Code hooks and monitoring-usage, Codex hooks and config-advanced, Cursor hooks, Copilot hooks-reference, OpenCode plugins and config schema.