aoa-session-progression-lift

aoa-session-progression-lift is a skill for Codex from 8Dionysus/aoa-agents. It costs 62 tokens per session (1,314 once invoked), scanned A, original, Apache-2.0.

A review workflow for turning completed session evidence into a limited candidate for agent progression, meaning a possible change in an agent’s development level.

In plain words
What is it for?
Use it after a closed and reviewed session with a baseline to record growth across several dimensions while leaving progression decisions to the responsible review systems.
Why use it?
It prevents one successful interaction or generated summary from being treated as proof of lasting improvement or authority.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it after a closed and reviewed session with a baseline to record growth across several dimensions while leaving progression decisions to the responsible review systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/8dionysus/aoa-agents/aoa-session-progression-lift
Install

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.

Any agent
npx skills add 8Dionysus/aoa-agents --skill aoa-session-progression-lift
Clone the repo
git clone --depth 1 https://github.com/8Dionysus/aoa-agents

Made for: Codex.

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.

agentmods badge for aoa-session-progression-lift

README.md
[![agentmods](https://agentmods.dev/badge/skills/8dionysus/aoa-agents/aoa-session-progression-lift/github.svg)](https://agentmods.dev/skills/8dionysus/aoa-agents/aoa-session-progression-lift)
Your own site
<a href="https://agentmods.dev/skills/8dionysus/aoa-agents/aoa-session-progression-lift"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-agents/aoa-session-progression-lift/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.

agentmods 80×15 button for aoa-session-progression-lift

Your own site · 80×15
<a href="https://agentmods.dev/skills/8dionysus/aoa-agents/aoa-session-progression-lift"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-agents/aoa-session-progression-lift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.01314
Opus 5 $0.00031 $0.00657
Sonnet 5 $0.00012 $0.00263
Haiku 4.5 $0.00006 $0.00131

Measured 11d ago against content hash eff4cf40d70d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aoa-session-progression-lift 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 11d 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.

skills/aoa-session-progression-lift/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aoa-session-progression-lift

Intent

Make observed agent growth legible without turning one success, a mood, or a generated summary into progression truth. The result is an owner-review candidate; aoa-agents keeps progression authority and aoa-evals keeps proof.

Owner-source return

Resolve the canonical aoa-agents root before any owner-relative read:

  1. Record <bundle_dir> as the absolute directory containing the SKILL.md actually loaded; never resolve from the task working directory. Initialize one unresolved <source_route> and <owner_root>.
  2. In one tool turn containing no other read or command, inspect exactly one same-bundle handle: <bundle_dir>/.aoa-skill-source.json. Await its result. If it is a regular file, set <source_route> to source-handle and require schema aoa_skill_source_receipt_v1 or aoa_skill_source_receipt_v2, this bundle name, owner aoa-agents, version 0.2.5, an existing absolute owner_root, a safe relative source_path, and <owner_root>/<source_path>/SKILL.md. For v2 also require non-empty digest, source_fingerprint, source_fingerprint_scope, and prompt_description_sha256. When capability_graph_hash is present, require it to be a non-empty string and preserve it. If the path exists but is invalid, mismatched, or not a regular file, return blocked_missing_owner_source; do not try another location.
  3. Only when that exact same-bundle handle path does not exist, set <source_route> to git and run git -C <bundle_dir> rev-parse --show-toplevel exactly once. Require the returned root's skills/port.manifest.json to declare the expected owner, bundle, and path.
  4. In the next tool turn, read only <owner_root>/skills/port.manifest.json; do not include an owner document, bundle reference, evidence read, or unrelated command in that tool turn. Await the manifest result. In the source-handle branch, require the same owner_repo, bundle name, and bundle path as the handle. In the git branch, require aoa-agents, this bundle name, and its actual bundle path. If the manifest read shared a tool batch with an owner document, the serial gate was not observed: return blocked_owner_source_gate_not_observed and do not use either result.
  5. Only after the successful manifest result, use a later tool turn to read exactly the two named owner-model documents below. Then owner-source resolution is complete. Do not run or retry the other source branch, including after a later owner-document read fails. Any handle, git, manifest, path, or owner mismatch returns blocked_missing_owner_source and ends this invocation.
  6. Never use find, rg --files, parent traversal, sibling scans, workspace conventions, temporary fixtures, .system, or another skill directory to discover a substitute owner root.

Read the full file on GitHub · 110 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 110 lines · 62 tokens per session scan A eff4cf40d70d

Subscribe to this mod's changes

aoa-session-progression-lift is a skill published in the GitHub repository 8Dionysus/aoa-agents (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,314 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 2026-08-31.

Related

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…

8Dionysus/aoa-memo · 116 tokens

aoa-memo-writeback

Use only before any memo artifact exists to decide whether live-session, closeout, landed-work, PR, diff, or review evidence yields one guarded memo candidate, export, or no-write result. If a concrete memo candidate, export, object, corpus, lifecycle, or read-model target already exists, use aoa-memo. Do not use for…

8Dionysus/aoa-skills · 95 tokens

aoa-eval

Select or apply an owner-local or cross-repository eval, route a confirmed no-fit to intake/design, or classify supplied session hits as eval candidates. Do not use for central proof bundles, named results or verdicts, source-linked reports, proof lifecycle, ordinary tests, undefined invariants, or generic session…

8Dionysus/aoa-skills · 68 tokens

aoa-checkpoint-closeout-bridge

Carry provisional checkpoint hints into a reviewed session closeout: harvest, progression, quest-promotion, and branch handoff. Use to collect bounded hints or execute after the current session artifact is closed and reviewed. Do not use mid-session for final judgment, without reviewed evidence, as a hidden playbook…

8Dionysus/aoa-skills · 76 tokens

aoa-knowledge-stewardship

Sanitize private technical material into a public-safe owner-bounded derivative, or resolve authority among authored, generated, runtime, and installed sources. Use for governed incidents, logs, configs, diagnostics, or conflicting source roles. Do not use for ordinary editing, memo/session work, direct publication…

8Dionysus/aoa-skills · 72 tokens

aoa-decision

Find, record, correct, or supersede a durable repository decision and its derived indexes. Use for prior rationale, a meaningful accepted choice, or decision-source/index drift. Do not use for ordinary documentation, an open choice, current source-authority conflicts, or runtime/generated authority mapping.

8Dionysus/aoa-skills · 62 tokens