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 agentmods add commands/skymanbp/codeeraser/updategit clone --depth 1 https://github.com/skymanbp/CodeEraserWhat 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 | $0.00015 | $0.00375 |
| Opus 5 | $0.00008 | $0.00187 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the update check through the plugin's own starter and relay its answer:
sh "${CLAUDE_PLUGIN_ROOT}/bin/ce.sh" update
The exit code is the verdict — 0 current, 1 newer release available, 2 unknown
(no network, or the release's manifest could not be read). On 0 the last line is
latest: <version> — up to date and on 2 latest: unknown — <reason>, and there
is nothing to run. An action line follows only on 1, and it names the ONE action
for this install; follow it exactly and do not substitute another:
- plugin's bound copy — reported when the starter's own pinned copy in
CLAUDE_PLUGIN_DATAran (an installer-placedceon PATH reports the installer-sidecar case below instead, even under this command): tell the user to run/plugin update codeeraser— the plugin's next manifest carries the new pins, and the starter re-verifies and re-downloads on the next session. Never runce update --yeshere: the starter would refuse a binary its manifest does not pin. - cargo install:
cargo install codeeraser. - placed by hand / installer sidecar:
ce update --yesreplacesceandce-corein place, verified against the release commit's pins; add--installerto also save the verified GUI installer and print its path.
Report the current and latest versions, the verdict, and the action in one short message. Do not download anything yourself.
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.
- yesterday First seen · 31 lines · 15 tokens per session scan A 931ecaa0f81b
update is a command published in the GitHub repository skymanbp/CodeEraser (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 375 once invoked, about $0.0001 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 commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
create_handoff
Create handoff document for transferring work to another session.
brainblast-deploy-plan
Deployment Intelligence for Anchor programs. Run before anchor deploy so you know how much SOL you need and the exact ordered transaction sequence — instead of working it out by hand.
reviewers
Suggest reviewers for a change, grounded on an active-owner model rather than a platform's naive last-touch blame.