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 fork-gap-fill-reconstructiongit 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/fork-gap-fill-reconstruction)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/fork-gap-fill-reconstruction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/fork-gap-fill-reconstruction/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/fork-gap-fill-reconstruction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/fork-gap-fill-reconstruction.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 | $0.00026 | $0.00394 |
| Opus 5 | $0.00013 | $0.00197 |
| Sonnet 5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
fork-gap-fill-reconstruction 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 6d 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.
What it actually says
SKILL: Fork Gap-Fill Reconstruction
Domain: multi-agent
Trigger: Apply when a forked or resumed child workflow must inherit prior replacement decisions even though its local transcript lacks full replacement records.
Source Pattern: Distilled from reviewed multi-agent coordination and child-runtime patterns.
Core Method
Rebuild child state from the records the child actually persisted, then fill any uncovered IDs from the parent's live replacement map. This handles the fork-resume case where inherited replacements were applied during the original run but never written as new child records. The result is a child state that replays the same cached previews the model originally saw instead of freezing those IDs as unreplaced gaps.
Key Rules
- Reconstruct from local records first so the child transcript remains the primary source of truth for what it explicitly persisted.
- Use parent replacements only as a gap-fill for IDs still present in the resumed messages and not already covered by child records.
- Preserve the
seenIdsfreeze semantics while layering in inherited replacements so resumed children do not recalculate different decisions. - Skip inherited mappings for IDs absent from the resumed message set; they are inert and should not pollute the child state.
Example Application
When a forked review agent resumes from sidechain transcript records, rebuild its replacement state from those records and then copy any missing preview strings from the parent’s live replacement map so the resumed child continues using the exact previews it saw before the interruption.
Anti-Patterns (What NOT to do)
- Do not rely on child records alone for fork-resume cases; inherited replacements may never have been persisted by the child.
- Do not blindly copy the entire parent replacement map into the child; only IDs present in the resumed messages should be imported.
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.
- 6d ago First seen · 28 lines · 26 tokens per session scan A 9ea0198a7bb4
fork-gap-fill-reconstruction is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 394 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 2026-09-03.
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.
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.