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 ychampion/cskill-agents --skill wire-shape-aligned-budgetinggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/wire-shape-aligned-budgeting)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/wire-shape-aligned-budgeting"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/wire-shape-aligned-budgeting/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/ychampion/cskill-agents/wire-shape-aligned-budgeting"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/wire-shape-aligned-budgeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.00475 |
| Opus 5 | $0.00015 | $0.00237 |
| Sonnet 5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
wire-shape-aligned-budgeting 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 8d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Wire-Shape Aligned Budgeting
Domain: tool-result-budget
Trigger: Apply this when building user messages that include multiple tool_result blocks to ensure the total stays under max tool results per message chars before the API call.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Apply budgeting at the same level the wire protocol actually sends data: one outbound user message at a time. For each message, find the tool-result blocks that are eligible for replacement, immediately reapply any replacement decisions that were already frozen on earlier turns, and then compact the smallest number of newly oversized results needed to get under the limit. Persist or offload those large results, replace them with stable previews, and record the decision so retries, resumes, and forks keep producing the same message shape.
Key Rules
- Treat replacement state as durable budgeting history; clone it for forks instead of mutating a shared object in place.
- Skip non-text or explicitly exempt results rather than trying to compact binary or protected payloads.
- Select new candidates by their original size, not by their preview size, so the algorithm removes the biggest pressure first.
- Reapply the exact stored preview for previously compacted results so prompt-cache shape stays stable across turns.
- Mark a decision durable at the same time you emit its preview so future turns do not re-decide the same result differently.
Example Application
If a single user message contains several large tool results, run this budgeting pass before the API call. The largest fresh results get persisted and replaced with previews until the message fits, while already-compacted results keep their exact prior preview text.
Anti-Patterns (What NOT to do)
- Avoid touching a message twice in the same turn; a second pass would reapply replacements again and break prompt-cache determinism.
- Don’t treat
frozenIDs as fresh candidates; once a tool_result is seen, its fate is locked. - Don’t persist results that already fit the budget just to create extra records—compact only when the limit is exceeded.
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.
- 8d ago First seen · 30 lines · 30 tokens per session scan A 608bc8ba77ad
wire-shape-aligned-budgeting is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 475 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.