Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/add-agent-support)<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/add-agent-support"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/add-agent-support.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00103 | $0.02073 |
| Opus 5 | $0.00051 | $0.01037 |
| Sonnet 5 | $0.00021 | $0.00415 |
| Haiku 4.5 | $0.00010 | $0.00207 |
Grade A, and why
add-agent-support 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Agent Support
Mission
Use this skill to deliver maintainable AgentSessions provider support, not just to block bad providers. The gate phase exists to prevent unsupported work from entering the repo; when gates pass, continue through implementation, QA, review, documentation, and release-ready communication.
Do not implement, merge, release, bump verified versions, or market provider support from docs, vendor claims, or synthetic fixtures alone.
Before coding, prove:
- The provider is usable from the user's region.
- The product/docs/UI are usable in English, unless the user explicitly accepts a non-English support burden.
- A free or existing plan can create enough real sessions for parser QA.
- Installation and auth are practical on this Mac.
- Real local transcript/session data can be generated or obtained.
- Redacted fixtures can preserve real keys, event names, timestamps, and content shape.
If a hard gate fails, reject or defer politely and clean up test-only installs/state before finishing.
Required Workflow
-
Start a support plan.
- Run
scripts/new_agent_support_plan.pyto create the plan scaffold. - Fill it with evidence, exact dates, URLs, command output, local paths, and blocker status.
- Keep uncertainty labeled as
Hypothesis:until verified. - Use
references/agent-provider-gates.mdfor hard gates and binary lifecycle details. - Use
references/agent-support-implementation.mdfor implementation, QA, review, and release details.
- Run
-
Classify the work.
new_provider: no current AgentSessions support. Run all gates, capture real sessions, then implement.existing_provider_update: provider exists. Useskills/agent-session-format-check/SKILL.mdandskills/agent-support-matrix/SKILL.mdbefore parser or version changes.public_claim: docs/release/social wording only. Verify implementation and test evidence before changing wording.
-
Prove the provider can be supported.
- Confirm region, language, account, plan, install, auth, and local-data availability.
- Ask before global installs, GUI app installs, browser extensions, logins, account linking, or networked agent runs.
- Snapshot pre-install binary/app/package/state paths before changing anything.
- Install or locate the official binary/app only after the research gate is plausible.
- Verify binary path, version, help output, app bundle metadata, auth behavior, and cleanup path.
What ships with it
4 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 · 145 lines · 103 tokens per session scan A ec1673b0c9cd
add-agent-support is a skill published in the GitHub repository jazzyalex/agent-sessions (846 stars, last pushed 3d ago), licensed MIT. It adds 103 tokens to every session and 2,073 once invoked, about $0.0005 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.