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/whitebite/opencode-dejavu/agents-mdgit clone --depth 1 https://github.com/WhiteBite/opencode-dejavuWhat 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 | $0.03465 | $0.03465 |
| Opus 5 | $0.01733 | $0.01733 |
| Sonnet 5 | $0.00693 | $0.00693 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade A, and why
opencode-dejavu AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Do NOT count exit 1 from diagnostic verbs (grep/tsc/pytest/curl/ls...) as failure — intended outcome; exit ≥ 2 always counts (OpenCode normalizes exits to 1, so discriminate by command shape) How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Generated: 2026-08-22 (refreshed 2026-08-30) Commit: 14ca0c1+ Branch: main
OVERVIEW
dejavu — OpenCode plugin ("memory prosthesis with teeth"): mechanically detects recurring tool-call failures and promotes them into enforced gates (3 failures across 2 distinct sessions). Remind first, hard-block on same-session repeat offense. TypeScript ESM, runs under Bun, ships as raw .ts (no build step).
STRUCTURE
dejavu-opencode-plugin/
├── index.ts # Plugin entry — exports Dejavu (Plugin factory) + all 4 hooks
├── src/
│ ├── patterns.ts # Pure engine: signatures, normalization, secret scrub, detection, blocking policy
│ ├── store.ts # GateStore/Stores: two-scope persistence, locks, promotion, TTL, migration, reconcile
│ └── validate.ts # Invariant layer: strict gate parsing + mechanical repair (parse-don't-validate boundary)
├── test/smoke.ts # Behavioral smoke test — plain bun script, no framework, temp-dir isolated
├── scripts/ # doctor.ts (pathology report), analyze.ts (store summary), migrate.ts (demote+scrub)
├── command/dejavu.md # /dejavu slash-command definition (install → ~/.config/opencode/command/)
├── skills/dejavu/ # Companion agent-protocol skill (install → ~/.config/opencode/skills/)
└── .omo/, .codegraph/ # Tooling artifacts — not project code
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| Gate enforcement (remind/block/override) | index.ts tool.execute.before |
session state lives ON THE GATE (remindedSessions/failedSessions), read fresh under the store lock |
| Failure detection + recording | index.ts tool.execute.after + event |
two channels: exit/text vs message stream; a cross-channel dedup guard counts one call once |
| Signature/normalization | src/patterns.ts |
callSignature, normalizeCommand, parameterizeError |
| Enforcement policy | src/patterns.ts:canBlock()/canRemind() |
three tiers — bash non-diagnostics block, diagnostics remind-only, everything else just watches |
| Persistence, locks, promotion, global escalation | src/store.ts |
Stores.recordFailure() is the core; cross-project evidence lives in global index.json |
| Self-healing / reconcile | src/store.ts + src/validate.ts |
Stores.reconcileAll() at every init; doctor --repair on demand |
| Tunables | top of index.ts and src/store.ts |
split: TTL/review caps in index, promote thresholds in store |
| Pathology checks | scripts/doctor.ts |
defect classes: unparseable/bad records, duplicate keys, temporal inversion, nested tokens, enforced-without-evidence, stale blocking/reminding, not-teaching, annoying, review-flagged, reminders-ignored, unsanitized, stale copies, corrupt logs, version drift, cross-store index checks; no-arg run discovers projects from the index |
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 · 134 lines · 3,465 tokens per session scan A 3cc561845bce
opencode-dejavu AGENTS.md is an instructions file published in the GitHub repository WhiteBite/opencode-dejavu (5 stars, last pushed 2d ago), licensed MIT. It adds 3,465 tokens to every session, about $0.0173 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cicero AGENTS.md
Instructions for 5uck1ess/cicero, covering agent guidance, product boundary, toolchain, verification and reliability and security invariants.
cicero CLAUDE.md
Instructions for 5uck1ess/cicero, a project described as: Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work to agents that ship PRs. Local STT/TTS; real-time voice client for ACP.
sid-code CLAUDE.md
Instructions for rushengzhou/sid-code, covering sid-code — 长在企业研发环境里的 coding agent, 北极星：长期宗旨与方向（最高纲领，长期不变）, 四大特性（能演示）, 四大方向（能复算 · 按 release 出一条曲线） and 主指标：四条方向必然互斥，需要一个仲裁者.
ob-1 AGENTS.md
Instructions for Overbrilliant/ob-1, covering agents.md, project index, stack, commands and key files.
vibe-codr AGENTS.md
Instructions for robzilla1738/vibe-codr, covering agents.md — vibe-codr, stack & layout, commands, visible tui change and conventions.
lfcode AGENTS.md
Instructions for lfyxhappy/lfcode, covering project structure, issue records, build and test, branch names and commits and pr titles.