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 append-only-sidechain-transcriptsgit 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/append-only-sidechain-transcripts)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/append-only-sidechain-transcripts"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/append-only-sidechain-transcripts/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/append-only-sidechain-transcripts"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/append-only-sidechain-transcripts.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 | $0.00032 | $0.00350 |
| Opus 5.5 | $0.00013 | $0.00140 |
| Sonnet 5.5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
append-only-sidechain-transcripts 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 1mo 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: Append-Only Sidechain Transcripts
Domain: session-storage Trigger: Subagent transcript persistence must stay append-only so forked history can be resumed and sidechain readers see messages in strict chronological order. Source Pattern: Distilled from reviewed subagent orchestration, isolation, and lifecycle implementations.
Core Method
Model each subagent transcript as an append-only event log with explicit ordering links or sequence checkpoints. Persist the seed messages once at startup, then append only durable milestones as the run progresses, ignoring ephemeral stream fragments that are not worth replaying later. Advance the transcript cursor only after a durable record is safely written so resumes, forks, and sidechain readers can reconstruct history in strict order without duplication.
Key Rules
- Never rewrite, truncate, or backfill earlier transcript entries once they have been committed.
- Filter out ephemeral deltas and other transient stream fragments so the stored transcript contains only meaningful replay points.
- Advance the ordering cursor only after a durable write succeeds.
- Partition transcript storage by agent or workflow so replay stays local and sidechains do not collide.
Example Application
When a workflow manager resumes a paused child agent, it can replay the append-only transcript to rebuild context exactly once and continue from the last durable checkpoint.
Anti-Patterns
- Writing directly from raw streaming deltas or duplicating seed messages will corrupt the append-only history.
- Advancing the cursor before persistence succeeds can create gaps, races, or duplicate replay on resume.
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.
- 1mo ago First seen · 28 lines · 32 tokens per session scan A 384dfbee0383
append-only-sidechain-transcripts is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 350 once invoked, about $0.0001 per session on Opus 5.5. 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.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log, then draft only the root pages that have meaningful content and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.