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 8Dionysus/aoa-skills --skill aoa-session-recoverygit clone --depth 1 https://github.com/8Dionysus/aoa-skillsWrote 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/8dionysus/aoa-skills/aoa-session-recovery)<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-session-recovery"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-session-recovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-session-recovery"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-session-recovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.00794 |
| Opus 5 | $0.00038 | $0.00397 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
aoa-session-recovery 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aoa-session-recovery
Intent
Recover from recurring session or workflow failure without collapsing symptom, diagnosis, proposed change, executed change, and verified health into one claim.
Trigger boundary
Use this skill when:
- a closed, explicitly reviewed evidence packet needs diagnosis; or
- a reviewed diagnosis is ready for one bounded repair cycle at its real owner
Do not use this skill when:
- evidence is live, raw, unreviewed, or only a frustration note
- there is no diagnosis for repair, the target owner is unknown, or the route is a broad playbook-scale rollout
- the requested action would bypass approval, checkpoint, rollback, or owner law
Inputs
- one reviewed evidence packet or reviewed diagnosis, with refs, target and durable owners, constraints, execution request, approval posture, available bindings, checkpoint/rollback anchors, and known health surfaces
Outputs
- exactly one typed result from
references/contract.yaml: either asession-diagnosisorrepair-cycle-result, with evidence refs, claim and execution posture, actual effects, health evidence, uncertainty, and stop line
Procedure
| Mode | Use when | Reference |
|---|---|---|
diagnose |
Reviewed symptoms exist but causes, drift class, or owner are unresolved. | references/diagnose.md |
repair |
A reviewed diagnosis exists and one bounded repair can be prepared, executed, verified, blocked, or handed off honestly. | references/repair.md |
Mode: diagnose
Read and follow references/diagnose.md.
Mode: repair
Read and follow references/repair.md.
- Read
references/contract.yamland only the selected mode reference to EOF. - Execute exactly one mode. A diagnosis may hand off to a later repair, but an invocation must not manufacture a diagnosis and immediately mutate from it.
- Preserve the strongest posture actually proved.
prepared,executing,executed, andverifiedare different states.
Contracts
- reviewed session evidence is input, not durable memory or owner truth
- diagnosis is read-only; repair acts only through the target owner's available tool or repository binding and within the user's authorization
- a repair that changes state requires approval posture, pre-change checkpoint, executable rollback, bounded retries, post-change health checks, and cleanup
- execution success is not health verification; only observed checks support
verified, and failed checks trigger rollback or an explicit blocked state - technique records may explain lineage but are not runtime dependencies
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.
- 12d ago First seen · 91 lines · 76 tokens per session scan A 55b3aedefb4e
aoa-session-recovery is a skill published in the GitHub repository 8Dionysus/aoa-skills (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 76 tokens to every session and 794 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.