Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jazzyalex/agent-sessions --skill agent-support-matrixgit clone --depth 1 https://github.com/jazzyalex/agent-sessionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jazzyalex/agent-sessions/agent-support-matrix)<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/agent-support-matrix"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/agent-support-matrix.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00511 |
| Opus 5 | $0.00030 | $0.00255 |
| Sonnet 5 | $0.00012 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
agent-support-matrix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Support Matrix
Overview
Keep the support matrix and memory bank accurate, and gate updates with evidence so parsing regressions are avoided.
Quick Start
- Read
docs/agent-support/workflow.md. - Run the session-format check and read
results.<agent>.compatibility. - Compare latest available agent versions to
docs/agent-support/agent-support-matrix.yml. - 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.pbxprojMARKETING_VERSION. - Run
./scripts/agent_watch.py --mode weeklyand usecompatibility.verdictas the support answer.severityandrecommendationare legacy escalation fields, not support claims. - Use
references/impact-scan.mdto inspect upstream releases for format changes. - Follow
references/update-checklist.mdbefore updating docs or fixtures.
Guardrails
- Do not bump
max_verified_versionwithout fixtures or sample logs plus passing parser tests. - Do not bump
max_verified_versionunlessresults.<agent>.compatibility.verdictissupports_latest, or the update explicitly records a narrower scope such assupports_installed_onlywith a blocker and follow-up. - If an agent does not log a version, keep
max_verified_version: "unknown"and document verification scope indocs/agent-json-tracking.md.
References
references/matrix-schema.mdfor matrix fields and update rules.references/impact-scan.mdfor format change detection heuristics.references/update-checklist.mdfor 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.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 52 lines · 59 tokens per session scan A a37b087b5f31
agent-support-matrix is a skill published in the GitHub repository jazzyalex/agent-sessions (846 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 511 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.