agentleFS
Sign inStart free
jazzyalexjazzyalex/agent-sessions/skills/agent-support-matrix/SKILL.md

agent-support-matrix

Skill941 starsChanged 9 days agoMITView on GitHub

Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 1 is distinctive, and 8 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.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the support matrix and memory bank accurate, and gate updates with evidence so parsing regressions are avoided.

    line 10
  2. Very specific:

    Run the session-format check and read results.<agent>.compatibility.

    line 16
  3. Very specific:

    If gaps exist, run an impact scan, collect evidence, and update fixtures/tests before bumping max_verified_version.

    line 18
  4. Very specific:

    Run ./scripts/agent_watch.py --mode weekly and use compatibility.verdict as the support answer.

    line 25
  5. Very specific:

    Use references/impact-scan.md to inspect upstream releases for format changes.

    line 28
  6. Very specific:

    Follow references/update-checklist.md before updating docs or fixtures.

    line 29
  7. Very specific:

    Do not bump max_verified_version without fixtures or sample logs plus passing parser tests.

    line 33
  8. Very specific:

    Do not bump max_verified_version unless results.<agent>.compatibility.verdict is supports_latest, or the update explicitly records a …

    line 34
  9. Very specific:

    If an agent does not log a version, keep max_verified_version: "unknown" and document verification scope in docs/agent-json-tracking.md.

    line 37

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Support Matrix

Overview

Keep the support matrix and memory bank accurate, and gate updates with evidence so parsing regressions are avoided.

Quick Start

  1. Read docs/agent-support/workflow.md.
  2. Run the session-format check and read results.<agent>.compatibility.
  3. Compare latest available agent versions to docs/agent-support/agent-support-matrix.yml.
  4. If gaps exist, run an impact scan, collect evidence, and update fixtures/tests before bumping max_verified_version.

Workflow

  • Determine the current Agent Sessions version from AgentSessions.xcodeproj/project.pbxproj MARKETING_VERSION.
  • Run ./scripts/agent_watch.py --mode weekly and use compatibility.verdict as the support answer. severity and recommendation are legacy escalation fields, not support claims.
  • Use references/impact-scan.md to inspect upstream releases for format changes.
  • Follow references/update-checklist.md before updating docs or fixtures.

Guardrails

  • Do not bump max_verified_version without fixtures or sample logs plus passing parser tests.
  • Do not bump max_verified_version unless results.<agent>.compatibility.verdict is supports_latest, or the update explicitly records a narrower scope such as supports_installed_only with a blocker and follow-up.
  • If an agent does not log a version, keep max_verified_version: "unknown" and document verification scope in docs/agent-json-tracking.md.

References

  • references/matrix-schema.md for matrix fields and update rules.
  • references/impact-scan.md for format change detection heuristics.
  • references/update-checklist.md for the evidence checklist.

Related Skills

  • agent-session-format-check — detection and evidence collection for session format drift, usage/limits tracking changes, OpenCode storage backend shifts, and discovery path contract failures. Use that skill for monitoring and diagnosis; use this skill for recording and gating version bumps.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free