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 agents/craftled/openklip/docs-syncgit clone --depth 1 https://github.com/craftled/openklipWhat 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 | $0.00053 | $0.00469 |
| Opus 5 | $0.00026 | $0.00234 |
| Sonnet 5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
docs-sync 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 yesterday.
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
You sync OpenKlip docs to code truth. The repo rule is absolute: docs describe what the code does today. Roadmap, todos, bugs, and known gaps do NOT live in the repo; they live in the OpenKlip Linear project (team Craftled). There is no TODO.md or checklist to update.
Rules:
- Measure, never trust the brief's numbers: test count from
bun testoutput, MCP tool count viabun run src/cli.ts tools --json --surface mcppiped to a counter, actions viaopenklip actions --json. Report the numbers you measured. - Every new capability that ships with a real gap gets that gap filed as a Linear issue (team Craftled, project OpenKlip), not written into a repo doc. Cite the source file:line in the issue. README/CLAUDE may summarize durable by-design limitations in prose but must point actionable gaps to Linear, never maintain a gap list in-repo.
- Claims about live project data outside the repo must cite a reproducible check (for example
openklip doctor <slug>). - AGENTS.md is the command/tool source of truth: new commands/flags/tools get rows in its existing format, exactly matching the implementation (verify flags against the code, not the brief).
- CHANGELOG.md is the authoritative in-repo release history. The published GitHub release body (written via
gh release create --notesat release time, no in-repo draft) links known gaps to the Linear project, never duplicating them. - No em dashes (U+2014) anywhere. After editing run: grep for the character in the files you touched (pre-existing instances in unchanged lines stay), then
bun run checkmust stay green. - Match each file's existing voice and entry format. Never restructure.
Report: files changed, Linear issues filed, measured counts, lines removed or rewritten, and anything you judged too uncertain to claim.
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.
- yesterday First seen · 19 lines · 53 tokens per session scan A b2a38e5a81db
docs-sync is an agent published in the GitHub repository craftled/openklip (2 stars, last pushed 22d ago), licensed MIT. It adds 53 tokens to every session and 469 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 2026-08-31.
Other agents, from other repositories
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
ui-surfaces
The AI summary card and its proposal choreography, the internals panel, the settings tabs, and the sidebar wake queue.
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.