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 agentmods add skills/zengliangyi/chatcrystal/chatcrystal-task-writebacknpx skills add ZengLiangYi/ChatCrystal --skill chatcrystal-task-writebackgit clone --depth 1 https://github.com/ZengLiangYi/ChatCrystalWrote 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/zengliangyi/chatcrystal/chatcrystal-task-writeback)<a href="https://agentmods.dev/skills/zengliangyi/chatcrystal/chatcrystal-task-writeback"><img src="https://agentmods.dev/badge/skills/zengliangyi/chatcrystal/chatcrystal-task-writeback.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.01036 |
| Opus 5 | $0.00031 | $0.00518 |
| Sonnet 5 | $0.00012 | $0.00207 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
chatcrystal-task-writeback 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatCrystal Task Writeback
Use this skill after meaningful work completes. Let ChatCrystal Core decide whether a memory should be skipped, merged, or created.
Workflow
- Trigger only after substantive work completes and the result produced reusable knowledge.
- Good candidates include:
- a durable fix
- a meaningful pitfall
- a reusable pattern
- an explicit engineering decision
Quality Gate Preflight
Before calling write_task_memory, verify the candidate is an experience asset, not a work log.
Do not call write_task_memory when:
- The summary only says what changed, without why it mattered.
- There is no clear problem, decision, pitfall, resolution, or reusable pattern.
- The task produced no durable lesson for future work.
Required field shape by memory.outcome_type:
fix: includeroot_causeorresolution.pitfall: includepitfallsplusresolutionorreusable_patterns.decision: includedecisions.pattern: includereusable_patterns.
Write memory.summary as a durable experience conclusion, not as "I did X".
Automatic writeback must include source_run_key; without it, emit a structured candidate for later save instead of silently writing manual memory.
- If
write_task_memoryis available and the runtime has a stable run or session key, call it with:mode: "auto"source_run_key: the stable run or session keytask.goal,task.task_kind,task.project_dir,task.cwd,task.branchtask.source_agentwhen knownmemory.summary: concise and durable, not chattymemory.outcome_type: one ofpitfall,fix,pattern,decisionmemory.root_cause,memory.resolution,memory.error_signatures,memory.files_touched,memory.tagswhen relevant
- Use
mode: "manual"only for an explicit manual save flow, never as a silent fallback for automatic writeback. - Default to project-scoped knowledge. Only use global scope for clearly cross-project knowledge and only in an explicit manual save flow.
- Report the persistence result accurately:
createdmergedskipped
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 113 lines · 62 tokens per session scan A 9da98e208b13
chatcrystal-task-writeback is a skill published in the GitHub repository ZengLiangYi/ChatCrystal (58 stars, last pushed 2d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,036 once invoked, about $0.0003 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
raytsystem-save
Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.
workspace-knowledge-sync
Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger…
workspace
Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.
mistakes
List past mistakes engram has learned in this project — failures, regressions, broken assumptions. Use before starting a non-trivial change to surface relevant prior failures, or when debugging to check if this issue has been seen before.
query
Query engram's local knowledge graph for structural context — function calls, imports, type relationships, mistake history, ADRs. Use when the user asks "how does X work in this project", "what calls Y", "where is Z used", or any structural question that doesn't need file content.
audit-history
Use when reviewing past agent sessions, auditing memory health, identifying repeated corrections or friction, cleaning up stale memories, proposing new skills and rules from usage patterns, or identifying mechanical improvements (testing, linting, static analysis, tooling) that could improve outcomes.