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 instructions/code-yeongyu/senpi/agents-mdgit clone --depth 1 https://github.com/code-yeongyu/senpiWhat 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 | $0.04113 | $0.04113 |
| Opus 5 | $0.02056 | $0.02056 |
| Sonnet 5 | $0.00823 | $0.00823 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
senpi AGENTS.md 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senpi Repository Guide
Generated: 2026-08-24
Commit: baf15a54d
Branch: initdeep-refresh-20260824
Senpi is an extension-first coding-agent monorepo. Keep changes scoped, preserve upstream mergeability, and read the nearest AGENTS.md plus every applicable changes.md before editing.
MANDATORY EXECUTION PROTOCOLS — NON-NEGOTIABLE
PROTOCOL 1 — EXPLICITLY REQUESTED MODIFICATIONS
WHEN A PATCH MUST BE MADE TO THIS REPOSITORY AND THE USER HAS EXPLICITLY INSTRUCTED THE MODIFICATION, THE FOLLOWING SEQUENCE IS ABSOLUTE AND BINDING. EXECUTE EVERY STEP, IN THIS EXACT ORDER. SKIPPING, REORDERING, OR ABBREVIATING ANY STEP IS A DEFECT:
- EXPLORE — READ EVERY FILE, SYMBOL, AND TEST THE CHANGE TOUCHES BEFORE WRITING A SINGLE LINE.
- MAKE A PLAN — A DECISION-COMPLETE PLAN EXISTS BEFORE ANY CODE.
- ADD TODOS IN ULTRA-DETAIL — MIRROR EVERY ATOMIC PLAN STEP INTO THE TODO LIST.
- MAKE A NEW WORKTREE — NEVER IMPLEMENT IN THE SHARED WORKTREE.
- MAKE A PR AND WORK UNTIL IT GETS MERGED — AN UNMERGED PR IS UNFINISHED WORK.
- SET A GOAL AND RUN THE ULW LOOP — EVERY SUCCESS CRITERION PASSES WITH CAPTURED EVIDENCE.
- MANAGE TODOS OBSESSIVELY — UPDATE ON EVERY STATE TRANSITION. A STALE TODO LIST IS A DEFECT.
DELIVERY STOP INVARIANT: UNDER PROTOCOL 1, “PR OPENED” IS NEVER A VALID STOP CONDITION, GOAL SUCCESS CRITERION, OR FINAL TODO. DELIVERY ENDS ONLY WHEN GITHUB REPORTS MERGED AND THE TASK WORKTREE IS REMOVED. WHILE GATES ARE PENDING, KEEP MERGE/CLEANUP TODOS OPEN, MONITOR TO COMPLETION, THEN MERGE-COMMIT AND CLEAN UP BEFORE THE FINAL RESPONSE.
PROTOCOL 2 — USER-REQUESTED PR REVIEWS
WHEN THE USER REQUESTS A PR REVIEW, YOU MUST:
- MAKE A NEW WORKTREE — CREATE A DEDICATED GIT WORKTREE AND PULL THE PR BRANCH INTO IT. NEVER CHECK THE PR OUT IN THE SHARED WORKTREE.
- REVIEW INSIDE THAT WORKTREE — RUN THE FULL REVIEW (READ, BUILD, TEST, QA) THERE.
- CLEAN UP WHEN THE REVIEW IS DONE — THE MOMENT THE REVIEW IS FINISHED, REMOVE THE WORKTREE (
git worktree removeTHENgit worktree prune). A LEFTOVER REVIEW WORKTREE IS A DEFECT.
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.
- yesterday First seen · 151 lines · 4,113 tokens per session scan A 13e6b95b869a
senpi AGENTS.md is an instructions file published in the GitHub repository code-yeongyu/senpi (411 stars, last pushed yesterday), licensed MIT. It adds 4,113 tokens to every session, about $0.0206 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 2026-08-30.
Other instructions, from other repositories
Lody AGENTS.md
Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
autolith AGENTS.md
Instructions for lambda-symbolics/autolith, covering repository guidelines, purpose and sources of truth, upstream references, architectural guardrails and package policy.
supercli AGENTS.md
Instructions for yashdev9274/supercli, covering agent instructions for supercode monorepo, build commands, root level commands, individual app/package commands and package-specific commands (run from package directory).
cocode AGENTS.md
Instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
copperhead AGENTS.md
Instructions for copperheadhq/copperhead, covering agents.md, repository overview, sources of truth, build and verification and architecture.