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-harvestgit 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-harvest)<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-session-harvest"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-session-harvest/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-harvest"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-session-harvest.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 | $0.00092 | $0.01085 |
| Opus 5.5 | $0.00037 | $0.00434 |
| Sonnet 5.5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
aoa-session-harvest 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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aoa-session-harvest
Intent
Metabolize reviewed experience without collapsing extraction, object classification, promotion, route choice, and automation readiness into one generic candidate label. Destination owners retain all acceptance authority.
Trigger boundary
Use this skill when:
- an explicitly reviewed, bounded session/evidence packet contains reusable units, an isolated unit needs owner or promotion judgment, several next routes must remain visible, or a repeated manual route needs automation triage
- the same extraction or promotion is explicitly requested from live,
unreviewed, or unbounded material and the only valid result is
blocked_unreviewed_evidencebefore a mode loads
Do not use this skill when:
- the request is generic summarization, progression scoring, memo writeback, runtime repair, or direct owner writing, promotion, scheduling, delegation, or mutation
- the request starts from ordinary work/closeout evidence and asks whether a
bounded lesson should be preserved for future owner work; that first
writeback judgment belongs to
aoa-memo-writeback, even if the answer might later resemble a candidate classification
Inputs
- reviewed evidence boundary and at least one literal supplied ref, closure/review posture, one mode intent, relevant owner constraints, risks, effects, and optional checkpoint/handoff hints that have not yet been trusted; or an attempted live/unreviewed input used only to return the pre-mode block
Outputs
- one typed session-local result from
references/contract.yaml, with evidence refs, owner hints, rejected nearest route, effectnone, stop line, and destination-owner review requirement; orblocked_unreviewed_evidence
Procedure
| Mode | Use when | Reference |
|---|---|---|
extract |
Reusable units and unresolved residue have not been isolated. | references/extract.md |
classify |
One unit needs its object kind, owner, and next artifact classified. | references/classify.md |
promote |
Exactly one isolated repeated quest-shaped unit needs a final promotion verdict. | references/promote.md |
branch |
Several materially different continuations must stay visible. | references/branch.md |
automation-opportunity |
A repeated manual route needs readiness and highest-honest-mode classification. | references/automation-opportunity.md |
What ships with it
7 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.
- 1mo ago First seen · 121 lines · 92 tokens per session scan A b8ad34ecf6b0
aoa-session-harvest is a skill published in the GitHub repository 8Dionysus/aoa-skills (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,085 once invoked, about $0.0004 per session on Opus 5.5. 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
aoa-memo
AoA/Abyss durable memory and owner orientation: use when ongoing work may depend on reviewed prior decisions, provenance, lifecycle/currentness, or an existing memo artifact, even when none is named. Also use to recall, review, or evolve a candidate, export, quarantine packet, object, corpus identity, lifecycle…
git-ai-search
Search and restore AI conversation context from git history.
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
ctx
Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an investigation, search prior sessions to ground yourself in earlier context. Use ctx blame to trace a line, file, commit, or PR to the agent session that produced it. Use…
deja-search
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.
deja-history
Search the user's past AI coding sessions. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you…