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 skills add Senpi-ai/senpi-skills --skill senpi-improve-tradesgit clone --depth 1 https://github.com/Senpi-ai/senpi-skillsWrote 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/skills/senpi-ai/senpi-skills/senpi-improve-trades)<a href="https://agentmods.dev/skills/senpi-ai/senpi-skills/senpi-improve-trades"><img src="https://agentmods.dev/badge/skills/senpi-ai/senpi-skills/senpi-improve-trades/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/skills/senpi-ai/senpi-skills/senpi-improve-trades"><img src="https://agentmods.dev/badge/skills/senpi-ai/senpi-skills/senpi-improve-trades.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 214 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Prompt Injection · line 442 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00457 | $0.14420 |
| Opus 5.5 | $0.00183 | $0.05768 |
| Sonnet 5.5 | $0.00091 | $0.02884 |
| Haiku 4.5 | $0.00046 | $0.01442 |
Grade B, and why
senpi-improve-trades scanned grade B with 1 finding 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 today.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **Never tell the user to "fund a position," "open a position first," "decide which gets action first," or How it starts
The opening of the file, as written. The whole thing — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senpi Improve My Trades — retrospective review + coaching
Router — first turn and every follow-up
On a follow-up, answer only what is new — never re-send the book table, book.total.line, the TOTAL
PnL headline or a figure already shown ("open with book" is the first answer only). Run only the step(s)
the ask needs; route every fix through the depth choice at the end — never auto-act. Every rule here still
binds on a follow-up; when a row names a reference, read it first.
| The ask | Run (review.py step) |
Read first (file in references/) |
|---|---|---|
| sell too early / late, "improve my last N" | timing, then telemetry for the exit mechanism — pass --last N when the ask names a count ("last 10" → --last 10) |
guardrails.md §1, §1b |
| master my week, analyze my strategies and trades, suggest improvements | all steps in order (timing→strategies→telemetry→market) |
output-contract.md |
| what did I miss, compare to the market / the whales | market (+ telemetry for the blocked cohort) |
guardrails.md §4; whales: compose senpi-smart-money |
| make more gains | strategies + telemetry |
guardrails.md §2–3 |
| shaken out, how my exits fire, why did it close, what is locked now | strategies + telemetry; senpi dsl closes / inspect (guardrail 6b) |
exit-records.md, sources.md |
| what my limits blocked | telemetry |
output-shape.md |
| where am I leaking, fees, maker vs taker | telemetry |
guardrails.md hard rule 0; output-shape.md, sources.md |
| walk me through my [asset] trade | (none — explain CLI) |
exit-records.md |
| why is [strategy] losing | strategies + telemetry |
guardrails.md §8; guardrail 5: judge it against its own mandate, all its wallets together, flat-by-design is not a loss |
| nothing to review, an empty result | read meta.book_state first |
no_strategies → senpi-market-pulse, then senpi-strategy-discover; no critique of an empty account ("Nothing to review?" below) |
| a saved wallet | review, master my week: the same steps; leaks, what did I miss: hand off to quant-desk |
"Your wallets" below |
the wallet picked from book.deep_dive.question |
go deep on that one | One book, rule 6; one-book.md |
| the user picks a fix depth | (none) | output-contract.md (both menus) |
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/event-log.md 4.8 KB
- references/exit-records.md 3.9 KB
- references/guardrails.md 8.5 KB
- references/one-book.md 1.6 KB
- references/output-contract.md 5.0 KB
- references/output-shape.md 16 KB
- references/sources.md 8.1 KB
- scripts/_yaml.py 14 KB runs code
- scripts/mcp_client.py 6.1 KB runs code
- scripts/review.py 190 KB runs code
- tests/fixtures/events_fixture.json 3.3 KB
- tests/fixtures/ratchet_stop_list_real.json 33 KB
- tests/fixtures/registry/installed_runtimes.json 4.6 KB
- tests/fixtures/review_fixture.json 5.1 KB
- tests/fixtures/review_mixed_status_fixture.json 3.9 KB
- tests/test_book_state.py 3.6 KB runs code
- tests/test_hl_info_retry.py 5.0 KB runs code
- tests/test_improve_trades_skill_layout.py 29 KB runs code
- tests/test_main_wallet_row.py 7.0 KB runs code
- tests/test_ratchet_attribution.py 11 KB runs code
- tests/test_review_external_wallets.py 54 KB runs code
- tests/test_review.py 80 KB runs code
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.
- today Changed 1478ab5b0908
- 3d ago Changed 3c909bfea352
- 7d ago Changed 31829c158586
- 8d ago Changed · +1 lines 147fb0286028
- 10d ago Changed · +1 lines 9e270bb7a301
- 14d ago Changed · -61 lines 7742b14e2662
- 21d ago Changed · +7 lines 3c70349607ff
- 28d ago Changed · +132 lines · +95 tokens per session 7211cdac4d10
- 1mo ago Changed · +107 lines 3b7e20a57bef
- 1mo ago First seen · 516 lines · 362 tokens per session scan B a5703e4556c8
senpi-improve-trades is a skill published in the GitHub repository Senpi-ai/senpi-skills (144 stars, last pushed yesterday), licensed MIT. It adds 457 tokens to every session and 14,420 once invoked, about $0.0018 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
senpi-improve-trades compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| senpi-improve-tradesSenpi-ai/senpi-skills | Skill | 144 | yesterday | MIT | B | 457 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |