Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Zenetusken/consolidate-memory/plugin install dream-beta-testerWrote 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/zenetusken/consolidate-memory/dream-beta-test)<a href="https://agentmods.dev/skills/zenetusken/consolidate-memory/dream-beta-test"><img src="https://agentmods.dev/badge/skills/zenetusken/consolidate-memory/dream-beta-test/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/zenetusken/consolidate-memory/dream-beta-test"><img src="https://agentmods.dev/badge/skills/zenetusken/consolidate-memory/dream-beta-test.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 | $0.00189 | $0.01595 |
| Opus 5 | $0.00095 | $0.00797 |
| Sonnet 5 | $0.00038 | $0.00319 |
| Haiku 4.5 | $0.00019 | $0.00160 |
Grade A, and why
dream-beta-test 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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream beta-test
Beta-test the consolidate-memory "dream" skill in a target repo and emit one structured,
version-stamped report. You are the dream skill's consumer / beta-tester — you run it
faithfully, instrument it, and report defects. You never patch the dream skill (nothing
under its plugin dir); this tooling ships as the dream-beta-tester plugin — its scripts live
under $CLAUDE_PLUGIN_ROOT/scripts/ and you run them from there.
The harness has two detectors and your job is to run both:
- a deterministic invariant oracle (already built:
beta_checks.py, driven byrun_beta.py) that re-tests known defect families every run — the trustworthy floor; - the judgment lenses (this skill's contribution) that you apply by hand to this run's actual artifacts to catch novel defects the families don't encode — the dynamic half.
Two properties make this worth doing, and everything below serves them:
- Dynamic, not overfit — adapt to whatever this run surfaces; never just re-run a frozen checklist. The oracle re-tests known classes; the lenses find new ones.
- Honest — a confident-wrong defect is worse than a missed one. The harness has already retracted two of its own hand-diagnoses, so every finding is re-verified against source before it is called confirmed, and suspected ones are quarantined, never counted.
Flow
1 · Run the deterministic engine
python3 "$CLAUDE_PLUGIN_ROOT/scripts/run_beta.py" --repo <TARGET_REPO> --test --json
--test (default) restores the store afterward — a pure beta-test that leaves no mutation;
default repo is cwd. The runner snapshots the store, runs the oracle (which drives the dream
skill's own read-only scripts from a clean subprocess pinned to the target repo),
renders a report to reports/<slug>__<version>__<ts>.md, diffs the store, and restores.
Note the consolidate-memory version under test (stamped in the report header) and the report path. Read the rendered report.
What ships with it
1 file 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.
- 9d ago First seen · 104 lines · 189 tokens per session scan A 784f836556dc
dream-beta-test is a skill published in the GitHub repository Zenetusken/consolidate-memory (6 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 1,595 once invoked, about $0.0009 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
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.