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/goalgit 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 | $0.00056 | $0.01270 |
| Opus 5 | $0.00028 | $0.00635 |
| Sonnet 5 | $0.00011 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
goal 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/goal — RALPH goal loop
Read-only Goal Board
Use the board for a compact, responsive progress view:
python3 scripts/goal_state.py board
python3 scripts/goal_state.py board <last_revision>
When a goal has a runtime attachment, this is projected from the event-backed
runtime and includes one foreground task, explicit presentation states,
bounded change deltas, suggestions, and task receipts. Without an attachment
it returns the same shape with authority: legacy-goal-state; that is a
compatibility projection, not runtime proof. The command is read-only and
never creates or advances a run.
Campaign spine and child-thread fleet
For a goal that fans out into several child tasks or host conversations, create one durable campaign spine and attach only the handles that the host actually returns:
python3 scripts/sips_campaign_fleet.py create "Improve SIPS" \
--campaign-id sips-overhaul \
--contract-json '{"acceptance":["tests pass","proof boundaries recorded"]}'
python3 scripts/sips_campaign_fleet.py attach sips-overhaul \
--child-id scout --title "Inspect archived task behavior" \
--role Scout --thread-id '<host-thread-id>'
python3 scripts/sips_campaign_fleet.py status sips-overhaul --markdown
The fleet projection chooses one foreground child, retains bounded recent
activity, and supports active, waiting, blocked, completed, failed,
canceled, archived, and reopen lifecycle transitions. Reopen creates a
new child incarnation; pass a new --thread-id or --task-id when a fresh host
or runtime binding already exists. Search keeps archived handles retrievable
without treating them as active sidebar work. The registry does not enumerate,
archive, or mutate host conversations; those remain a separate host proof
layer.
The same surfaces are available as the read-only
homebase_campaign_fleet_read and write
homebase_campaign_fleet_write MCP tools. A runtime run can join its campaign
automatically by carrying metadata.campaign_id; the Goal Board then includes
the campaign projection without changing runtime event authority.
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 · 118 lines · 56 tokens per session scan A 8da757e3836b
goal is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,270 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.
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.