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 skills/pallerana/agentic-loop-engineering-kit/loop-self-improvementnpx skills add pallerana/agentic-loop-engineering-kit --skill loop-self-improvementgit clone --depth 1 https://github.com/pallerana/agentic-loop-engineering-kitWhat 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 | $0.00040 | $0.01519 |
| Opus 5 | $0.00020 | $0.00759 |
| Sonnet 5 | $0.00008 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
loop-self-improvement 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Self-Improvement (Phase 9d)
Extract durable agent-facing learnings from a completed loop run. Do not update wiki (that's Phase 9c ce-compound).
When to run
- Profile has
self_improvement: true(or rationale-only fallback for--repowithout named profile) - Loop completed Phases 1–8 at L2/L3
- L1 loops skip 9d → orchestrator ends 9d with
NO_LEARNINGS/ skip (no contract emitted)
Emit NO_LEARNINGS when:
- L1 mode
self_improvement: falseon profile- Duplicate fingerprint with no new insight vs existing pattern/quirk
- No durable agent-facing learning from the run
Inputs
- Active profile YAML (
pattern_doc,known_quirks,repos) - Active
--repopath - JIRA key, PR URL, test names, failure router signals from the run
docs/loop-learnings/README.mdindex (fingerprint run counts)
Scope routing
| Scope | Min runs | Contract mode | Target |
|---|---|---|---|
| Single repo | 1 | loop_learning |
pattern_doc append + upsert_known_quirk |
context_skill |
2+ (1 if Phase 8 AC→test map) | promotion_proposal |
e.g. cell-health-mvp/SKILL.md |
| Profile family | 2+ | promotion_proposal |
springboot-default.yaml |
| Spring Boot all | 5+ | promotion_proposal |
java-springboot-standards.mdc |
| Ops | 1 | loop_learning |
ops-incident-patterns.md |
| PR review | 2+ | promotion_proposal |
pr-code-review.mdc |
| No profile | n/a | loop_learning |
rationale only (targets: []) |
Output (TOON contract)
Emit one shared <UTC-ts> = YYYYMMDDTHHMMSSZ per run.
- Rationale:
docs/loop-learnings/by-repo/<repo>/<JIRA-KEY>-<UTC-ts>.md - Learning contract:
docs/loop-learnings/contracts/<repo>/<JIRA-KEY>-<UTC-ts>-learning.json - Promotion (if threshold met):
docs/loop-learnings/pending-promotion/<scope>/<JIRA-KEY>-<UTC-ts>-promotion.json
Example loop_learning contract
{
"contract_version": "1",
"mode": "loop_learning",
"jira_key": "PROJ-153",
"fingerprint": "jacoco-cosmos-sdk-exclusion",
"scope": "single-repo",
"profile": "cell-health",
"repo": "your-service-cell-health-aggregator",
"rationale_path": "docs/loop-learnings/by-repo/your-service-cell-health-aggregator/PROJ-153-20260623T161430Z.md",
"targets": [
{
"path": "loop-kit/patterns/cell-health-patterns.md",
"action": "append_markdown",
"subsection": "Known Quirks (aggregator)",
"lines": [
"JaCoCo gate fails when Cosmos SDK internals measured; exclude com.azure.cosmos.* SDK classes."
]
}
],
"actions": [
{
"action": "upsert_known_quirk",
"profile": "cell-health",
"summary": "JaCoCo: exclude Cosmos SDK internals from measured scope"
}
]
}
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 · 164 lines · 40 tokens per session scan A e520ac603655
loop-self-improvement is a skill published in the GitHub repository pallerana/agentic-loop-engineering-kit (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,519 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…