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/rasputinkaiser/self-improvement-plugin/selfloopgit clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWhat 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 | $0.00029 | $0.00751 |
| Opus 5 | $0.00015 | $0.00376 |
| Sonnet 5 | $0.00006 | $0.00150 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
selfloop 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/selfloop — evidence-driven self-improvement loop
Parse the user's arguments:
/selfloop [focus]starts a new self-improvement loop.focusis optional./selfloop statusprints the current goal state./selfloop pauseand/selfloop resumecontrol the active loop./selfloop completemarks a genuinely finished loop complete./selfloop stopor/selfloop clearclears the goal and stops immediately.
Use ${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/goal_state.py for every state
transition. To start, run selfloop-set with the optional focus. For controls,
use the existing status, pause, resume, complete, and clear actions.
Immediately begin the first cycle after selfloop-set; do not wait for another
message.
Progress surface
For an attached runtime campaign, read the Goal Board:
python3 scripts/sips_runtime.py read --op board --json '{"run_id":"<run_id>"}'
Poll with since_revision to receive bounded event deltas. The board exposes
one foreground next action for a responsive operator surface while the runtime
may still have multiple bounded workers. Its labels are presentation aliases;
event digests, leases, and immutable receipts remain authoritative.
Scope lock
The loop's entire focus is improving SIPS or the agent operating it. Valid targets include reasoning quality, tool reliability, Memory Fabric recall, verification quality, context efficiency, autonomy, self-correction, and the proof surfaces that measure those capabilities. Do not drift into unrelated product work, cosmetic churn, score gaming, or changes without a measurable benefit.
One cycle
- Inspect current goal state and recall prior lessons for the relevant scope.
- Establish a baseline with SIPS status,
self_correct.py --json, the most relevant tests, and any direct runtime proof needed for the target. - Rank evidence-backed weaknesses by expected capability gain, confidence, recurrence, and implementation cost. Choose one. If uncertainty could change the choice, verify it before editing.
- State the candidate, baseline, expected gain, and acceptance check in one compact note.
- Run
/checkpoint, then implement the smallest reversible change that can produce the gain. - Run focused verification first, then the relevant SIPS regression checks. Compare against the baseline. Keep the change only when the evidence shows an improvement; otherwise repair it or restore the checkpoint.
- Record the cycle with
goal_state.py selfloop-record improved "<summary and proof>", append the result to the SIPS improvement ledger, and use/teachfor any durable lesson. - Increment the goal turn count and immediately begin the next cycle while the goal remains active.
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.
- 2d ago First seen · 75 lines · 29 tokens per session scan A abd41bbf619a
selfloop is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 751 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 2026-08-31.
Other commands, from other repositories
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
test
Design or run focused test validation for a task, bug, or diff.
mvp-spec
Research and produce a strict MVP spec with small 1-2 hour tasks and explicit out of scope.
research
Research a technical or product question.
review-pr
Command "review-pr" from saski/arnesto, covering review pr, what this command does, workflow steps, phase 0: initialize review and phase 1: analysis & summary.
evolution-engine
Scan feedback and generate evolution proposals for rule/skill upgrades.