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 XyrusCode/ai-sync --skill conversation-historygit clone --depth 1 https://github.com/XyrusCode/ai-syncWrote 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/xyruscode/ai-sync/conversation-history)<a href="https://agentmods.dev/skills/xyruscode/ai-sync/conversation-history"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/conversation-history/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/xyruscode/ai-sync/conversation-history"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/conversation-history.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 | $0.00069 | $0.01801 |
| Opus 5.5 | $0.00028 | $0.00720 |
| Sonnet 5.5 | $0.00014 | $0.00360 |
| Haiku 4.5 | $0.00007 | $0.00180 |
Grade A, and why
conversation-history 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 17d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation History Skill
Manage live session context to prevent token waste and goal drift.
Raw conversation transcripts quickly bloat with tool outputs, file contents, compiler diagnostics, and intermediate exploratory turns. This causes context rot: the model re-reads files it already saw, loses sight of the original task, and burns tokens on stale history.
This skill operates across two levels:
- Intra-session working context: Anchoring immediate objectives and pruning noisy tool outputs during execution.
- Project decision log (
CONVERSATION_HISTORY.md): Maintaining a committed chronological log in the repository that enables fast rehydration, records scope boundaries, and preserves exact verification proofs.
Non-Interference Rules (Zero Overhead)
- Never hunt for missing stores: If
~/.agents/memory/orMEMORY.mdis missing, skip it silently in zero turns. Never shell out looking forinstall.shor attempt to bootstrap an external store. - Never hunt for missing graphs: If
graphify-out/graph.jsondoes not exist, skip it silently. Do not run commands to build or install a graph during task execution. - No automatic memory promotion: Transient npm errors, build quirks, and local environment hiccups are not cross-project gotchas. Never chain into
memory-authoringautomatically at task completion. Only promote when explicitly instructed by the user. - Clean finish: When verification passes, record the outcome and stop. Never invent exit side quests.
When to use
- A conversation reaches 15+ turns or accumulates large tool outputs (test suites, build logs, file dumps).
- You notice the agent re-reading previously loaded files or drifting from the core task.
- Beginning a multi-phase implementation where each phase builds on previous decisions.
- Starting a fresh session and needing to rehydrate project context with minimal token spend.
- Winding down a session to record settled decisions, code changes, and test proofs in
CONVERSATION_HISTORY.md.
What ships with it
9 files 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.
- references/compaction-protocols.md 2.6 KB
- references/graphify-pairing.md 2.4 KB
- references/memory-pairing.md 2.3 KB
- references/objective-ledger.md 2.7 KB
- references/project-decision-log.md 2.8 KB
- templates/compaction-checkpoint.md 442 B
- templates/conversation-history-entry.md 880 B
- templates/objective-anchor.md 524 B
- templates/session-handoff.md 822 B
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.
- 17d ago First seen · 114 lines · 69 tokens per session scan A 8508055af8f6
conversation-history is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 18d ago), licensed MIT. It adds 69 tokens to every session and 1,801 once invoked, about $0.0003 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 2026-09-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.