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.
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWrote 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/commands/rasputinkaiser/self-improvement-plugin/recall)<a href="https://agentmods.dev/commands/rasputinkaiser/self-improvement-plugin/recall"><img src="https://agentmods.dev/badge/commands/rasputinkaiser/self-improvement-plugin/recall/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/commands/rasputinkaiser/self-improvement-plugin/recall"><img src="https://agentmods.dev/badge/commands/rasputinkaiser/self-improvement-plugin/recall.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 | $0.00013 | $0.00192 |
| Opus 5.5 | $0.00005 | $0.00077 |
| Sonnet 5.5 | $0.00003 | $0.00038 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Follow references/command-protocol.md.
Run python3 <plugin-root>/scripts/recall_ranker.py --query "$ARGUMENTS" --json.
Check scope, relevance, source identity, validity, and negative applicability.
Rank relevant failures and their verified corrections; unrelated failures do not
outrank an applicable lesson simply because they have a failure tag.
For a chain of conditional lessons, use method assumptions: identify premises,
evidence references, positive and negative support, and derivation rules. An
unsupported cycle establishes nothing. Recompute after withdrawing a premise.
An inconsistent premise can support competing conclusions; disclose that conflict.
This method does not verify cited sources or implement a complete ATMS.
Show why a lesson applies, what would invalidate it, and any missing verification. Separate user instructions from empirical claims. Return no match when appropriate.
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.
- 28d ago Changed · +1 lines · -2 tokens per session 1aea65c281bd
- 1mo ago First seen · 18 lines · 15 tokens per session scan A 25850d75409a
recall is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (8 stars, last pushed 13d ago), licensed MIT. It adds 13 tokens to every session and 192 once invoked, about $0.0001 per session on Opus 5.5. 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
sessions
Manage OpenAI Codex session history, aliases, and session metadata.
projects
List registered projects and instinct counts.
promote
Promote project instincts to global scope.
fechar-sessao
Closes the current work session — rewrites the Estado Atual section of AGENTS.md to reflect where things stand now.
retro
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
save-session
Save current session state to a dated file in /.codex/session-data/ so work can be resumed in a future session with full context.