provenance-trace
Skill152 starsChanged 4 months agoApache-2.0View on GitHub
Trace published DocMason knowledge objects or answer text back to evidence units and provenance records.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adapter-syncSkill
- askSkill
- grounded-answerSkill
- grounded-compositionSkill
- knowledge-base-syncSkill
- knowledge-constructionSkill
- retrieval-workflowSkill
- runtime-log-reviewSkill
- validation-repairSkill
- workspace-bootstrapSkill
- workspace-doctorSkill
- workspace-statusSkill
- operator-evalSkill
- public-sample-workspaceSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 5 are distinctive, and 10 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the task is to prove where a knowledge object or answer came from.
- Very specific: line 10
Use it directly for explicit provenance or citation requests, or let ask route here automatically.
- Distinctive: line 21
If the agent cannot inspect the local trace artifacts or source evidence, stop and explain that reliable provenance tracing is not possible.
- Very specific: line 25
Use current as the default knowledge-base target unless the task explicitly says otherwise.
- Very specific: line 29
if you genuinely need nested support objects or detailed render metadata, rerun full --json to a local file and inspect it selectively …
- Very specific: line 30
keep DocMason workspace commands sequential inside the same workspace session.
- Very specific: line 34
do not invent a new freeform --source-ref surface in this phase.
- Very specific: line 52
if the provenance judgment depends on nested artifact_supports, semantic_supports, overlay consumed inputs, covered slots, blocked slots, …
- Distinctive: line 53
If any segment is only partially grounded or unresolved, say so explicitly and avoid pretending stronger provenance than the trace supports.
- Very specific: line 55
If you need to export a scratch trace note and the user did not specify a destination, place it under runtime/agent-work/.
- Very specific: line 59
If render_inspection_required is true, inspect the cited render assets before claiming a confident conclusion.
- Distinctive: line 60
If the trace cannot resolve the requested source, session, or answer path, surface the not-found failure directly.
- Very specific: line 61
If the traced answer state is not grounded, qualify or abstain rather than overclaiming support.
- Very specific: line 62
If answer-first trace inherits an approximate or unresolved reference-resolution block, preserve that boundary in the provenance summary …
- Distinctive: line 74
When a trace says render inspection is needed, inspect the render assets before claiming a confident conclusion.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Provenance Trace
Use this skill when the task is to prove where a knowledge object or answer came from.
Use it directly for explicit provenance or citation requests, or let ask route here automatically.
Direct public trace remains a legal operator provenance surface.
It does not substitute for canonical ask when the user is really asking for ordinary answer completion.
Required Capabilities
- local file access
- shell or command execution
- ability to inspect structured JSON output
If the agent cannot inspect the local trace artifacts or source evidence, stop and explain that reliable provenance tracing is not possible.
Procedure
- Use
currentas the default knowledge-base target unless the task explicitly says otherwise. - For citation-first tracing, run:
docmason trace --source-id <source_id> --json --compact- optionally add
--unit-id <unit_id>for unit-level detail - if you genuinely need nested support objects or detailed render metadata, rerun full
--jsonto a local file and inspect it selectively instead of pasting the raw payload into chat - keep DocMason workspace commands sequential inside the same workspace session; do not overlap
trace,retrieve,sync,status, orvalidate-kbwhile a lease-owning command is still active
- For answer-first tracing, run:
docmason trace --answer-file <path> --json --compact- or
docmason trace --session-id <session_id> --json --compact - do not invent a new freeform
--source-refsurface in this phase; public trace remains ID-first
- Inspect:
payload_detail- any inherited
reference_resolutionblock on answer-first traces answer_state- source provenance
- unit consumers
- incoming and outgoing relations
- grounding status for each answer segment
- compact
supporting_source_ids - compact
supporting_unit_ids supporting_artifact_idssupporting_overlay_unit_ids- segment
support_lane_counts - segment
artifact_support_count - segment
semantic_support_count - artifact
focus_render_assetswhen present - render-inspection requirements
- if the provenance judgment depends on nested
artifact_supports,semantic_supports, overlay consumed inputs, covered slots, blocked slots, render refs,render_page_span,bbox,normalized_bbox, or sidecar paths, inspect a file-first full trace capture instead of the raw chat payload
- If any segment is only partially grounded or unresolved, say so explicitly and avoid pretending stronger provenance than the trace supports.
- Return the final provenance or groundedness judgment to the main agent instead of treating trace output as a final user answer by itself.
- If you need to export a scratch trace note and the user did not specify a destination, place it under
runtime/agent-work/.
Escalation Rules
- If
render_inspection_requiredis true, inspect the cited render assets before claiming a confident conclusion. - If the trace cannot resolve the requested source, session, or answer path, surface the not-found failure directly.
- If the traced answer state is not
grounded, qualify or abstain rather than overclaiming support. - If answer-first trace inherits an
approximateorunresolvedreference-resolution block, preserve that boundary in the provenance summary instead of silently upgrading it.
Completion Signal
- The workflow is complete when the main agent has a clear provenance summary, including any
answer_state, unresolved segments, and render-escalation requirements.
Notes
- Phase 4 tracing reads
knowledge_base/current/trace/by default. - Answer-first tracing stores structured local logs under
runtime/logs/. --session-idworks only for sessions that contain a reusable final answer.- In Phase 6b2, answer-first trace reuses the same shared reference-resolution contract already attached to the originating ask turn or retrieval session.
- When a trace says render inspection is needed, inspect the render assets before claiming a confident conclusion.
- Ordinary natural questions should usually begin at
ask, which can route here when provenance is the real intent.
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.

