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 decision-fate-freezinggit 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/decision-fate-freezing)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/decision-fate-freezing"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/decision-fate-freezing/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/decision-fate-freezing"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/decision-fate-freezing.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 | $0.00028 | $0.00464 |
| Opus 5 | $0.00014 | $0.00232 |
| Sonnet 5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
decision-fate-freezing 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 11d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Decision Fate Freezing
Domain: tool-result-budget Trigger: Apply when the message-level replacement budget runs and you need previously seen tool results to keep the same fate (persisted preview vs full content) even after resumes, forks, or cached prompts. Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Track every processed tool-result ID in durable budgeting state. Once a result has been evaluated, freeze its fate: either it stays inline forever or it is always replaced by the same persisted preview. Retries, forks, and resumed sessions must inherit that state and reapply the same decision instead of recalculating it. This keeps prompt shape stable and prevents the same result from flipping between full content and preview across turns.
Key Rules
- Mark an ID as decided as soon as it becomes eligible, even if the outcome is “leave inline,” so later turns never re-open the decision.
- Store replacement previews only after persistence succeeds, and keep the decision marker and replacement payload in sync.
- Clone or reconstruct this state when forking or resuming so child threads inherit the exact same budgeting history.
- Log or persist every new replacement so resumes reapply the same preview string and the prompt cache stays intact.
Example Application
If a large tool result is replaced with a persisted preview on turn 20, later retries and child agents should reuse that exact preview rather than reconsidering whether the full result can fit inline. The budgeting outcome for that result becomes part of the session state.
Anti-Patterns (What NOT to do)
- Do not mutate seen ids only after persistence finishes, or a concurrent reader may treat the ID as fresh and replace it again on the same turn.
- Do not skip cloning or reconstructing the state for cache-sharing forks; that leads to inconsistent decisions between parent and child and breaks prompt caching.
- Do not update the replacements map without also marking the ID as seen — the next turn would treat it as fresh and potentially try to persist the same content twice.
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.
- 11d ago First seen · 29 lines · 28 tokens per session scan A 86c8600736e5
decision-fate-freezing is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 464 once invoked, about $0.0001 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 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.
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.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.