context-budget-review
starsforks
How to install context-budget-review?
rlaope/oh-my-hermes/context-budget-review
$npx -y skills add rlaope/oh-my-hermes --skill context-budget-review[omh] Hermes Context Budget Review workflow: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work.
SKILL.md
| 1 | # Context Budget Review |
| 2 | |
| 3 | This is a Hermes-native `context-budget-review` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `context-budget-review` ports ECC's context-budget and token-budget instincts into OMH as a compactness gate that protects long-running work without redefining success around a smaller task. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The user asks for live token/cost telemetry; use `ops-observability-card`. |
| 12 | - The user asks to continue a loopable goal; use `loop` unless budget planning is the explicit blocker. |
| 13 | - The task is a short one-step answer with no meaningful context risk. |
| 14 | |
| 15 | ## Examples |
| 16 | |
| 17 | Good example: |
| 18 | |
| 19 | - Prompt: context-budget-review 이 장기 PR 작업에서 어떤 맥락을 꼭 유지하고 언제 요약해야 하는지 잡아줘. |
| 20 | - Expected behavior: Prepare context_budget_plan/v1, must_keep_context_pack/v1, checkpoint plan, risk register, and overflow recovery route. |
| 21 | - Why: The request is about preserving context quality during long-running agent work. |
| 22 | |
| 23 | Bad example: |
| 24 | |
| 25 | - Prompt: context-budget-review 토큰 아끼려고 원래 목표를 더 작은 목표로 바꿔줘. |
| 26 | - Expected behavior: Reject goal shrinking and instead compact context while preserving the full objective and evidence gaps. |
| 27 | - Why: Budget review optimizes context handling, not the user's requested end state. |
| 28 | |
| 29 | ## Completion Checklist |
| 30 | |
| 31 | - The run or workflow scope, metric window, failure modes, and cost/latency boundary are named. |
| 32 | - Local telemetry, provider truth, billing truth, and completion evidence are separate states. |
| 33 | - Warnings name the next measurement or operator review action. |
| 34 | |
| 35 | ## Recovery Notes |
| 36 | |
| 37 | - If provider metrics are unavailable, report only local metadata and mark provider truth not_observed. |
| 38 | - If cost or latency looks risky, surface a warning plus the next measurement rather than a completion claim. |
| 39 | |
| 40 | ## OMH Context Rail |
| 41 | |
| 42 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 43 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 44 | - Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `agent-board`, `gateway-intent-card`, `voice-operator`, `+26 more`) - schedules, status, health, and ops review. |
| 45 | - If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill. |
| 46 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 47 | - Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess. |
| 48 | - Coverage: Every generated workflow skill carries this rail. |
| 49 | - Normal users talk to Hermes; OMH CLI is infra. |
| 50 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 51 | |
| 52 | ## Use When |
| 53 | |
| 54 | Use before long-running research, coding, review, or multi-agent work when context, token, cost, or summary drift could break quality. |
| 55 | |
| 56 | Strong routing signals: `context-budget-review`, `context budget review`, `context budget`, `token budget review`, `token budget`, `prompt budget`, `context compaction`, `compact context`, `too much context`, `summarization checkpoint`, `budget this task`, `컨텍스트 예산`, `토큰 예산`, `컨텍스트 압축`, `요약 체크포인트` |
| 57 | |
| 58 | ## Catalog Metadata |
| 59 | |
| 60 | Category: `observability` |
| 61 | Phase: `context-budget-review` |
| 62 | Hermes role: `tracker` |
| 63 | Quality tier: `context-budget-gated` |
| 64 | |
| 65 | Quality bar: |
| 66 | |
| 67 | - Name must-keep context before summarizing or delegating long work. |
| 68 | - Separate durable requirements, volatile status, file refs, verification evidence, and open blockers. |
| 69 | - Define checkpoint cadence, overflow recovery, and continuity verification. |
| 70 | - Use bounded copy while preserving the full objective and evidence gaps. |
| 71 | |
| 72 | Handoff policy: |
| 73 | |
| 74 | Keep budget design and status narration in Hermes. Provider billing, exact token usage, runtime compaction, and executor cost evidence require observed wrapper, runtime, or provider data. |
| 75 | |
| 76 | Required inputs: |
| 77 | |
| 78 | - task or workflow scope |
| 79 | - expected duration, artifacts, and handoff surfaces |
| 80 | - available context sources and must-keep facts |
| 81 | - token, cost, latency, or message-size constraints when known |
| 82 | |
| 83 | Expected outputs: |
| 84 | |
| 85 | - context_budget_plan/v1 |
| 86 | - must_keep_context_pack/v1 |
| 87 | - summarization_checkpoint_plan/v1 |
| 88 | - budget_risk_register/v1 |
| 89 | - overflow_recovery_route/ |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
