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 gyanranjan/polyagent-skills --skill context-orchestratorgit clone --depth 1 https://github.com/gyanranjan/polyagent-skillsWrote 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/gyanranjan/polyagent-skills/context-orchestrator)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/context-orchestrator"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/context-orchestrator/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/gyanranjan/polyagent-skills/context-orchestrator"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/context-orchestrator.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 | $0.00060 | $0.00926 |
| Opus 5.5 | $0.00024 | $0.00370 |
| Sonnet 5.5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
context-orchestrator 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 2mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Orchestrator
Purpose
Create a canonical context/pack.md that consolidates requirements, architecture decisions, design readiness, task state, and traceability so agents can resume work reliably with minimal ambiguity.
When to Use
- User wants context engineering for long-running work
- Multi-agent or multi-session workflows need deterministic handoffs
- Project state is fragmented across requirement/spec/ADR/todo documents
- Team wants a standard "start here" context entry point before coding
When NOT to Use
- One-off simple tasks that do not require persistent context
- Purely creative tasks with no requirement/design traceability expectations
Inputs
Required:
- At least one source artifact (
requirements.md,spec.md, ADRs, oragent.todo.md)
Optional:
- GitHub repository/issues links
- RCA documents for recent incidents
- Preference for context size (
short,medium,full)
Process
Step 1: Collect Source Artifacts
Identify available sources in priority order:
- Requirements (
REQ-*,NFR-*) - Specs/design docs
- ADRs
agent.todo.md- RCA docs (if any)
If sources are missing, log explicit gaps rather than inferring silently.
Step 2: Build context/pack.md
Use references/context-pack-template.md and include:
- Current objective and phase
- Scope, constraints, and non-goals
- Active architecture/runtime/database/logging decisions
- Design readiness status
- Current execution plan and blockers
- Traceability map (
REQ-*-> spec -> issue/task)
Step 3: Sync Task and Traceability State
Update agent.todo.md using common-skills/agent-todo-ledger.md and scripts where available:
polyagentctl sync-todofor requirements/spec snapshotspolyagentctl init-issuesfor REQ-to-GitHub issue bootstrap
Step 4: Validate Context Pack Quality
Run deterministic checks:
polyagentctl verify-context-pack context/pack.md
polyagentctl design-check --allow-open docs/specs/SPEC_TEMPLATE.md
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.
- 2mo ago First seen · 119 lines · 60 tokens per session scan A c1c05eaf9d24
context-orchestrator is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 60 tokens to every session and 926 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
baton-pass
Pass the baton with a deterministic ACTIVECONTEXT.md snapshot so fresh context picks up the work. MANDATORY in Antigravity and Gemini when the breaker hook warns that the context estimate has reached 105k tokens (it blocks at 130k), before auto-compaction hits, or when asked to 'pass the baton', 'baton pass', 'save…
forgetful-context-gather
Gather deep context before planning or implementing — one pass that turns a task description into a cited context pack: relevant decisions, patterns, constraints, code pointers, procedures, and explicit gaps. Runs recall from several angles, explores the graph around the strongest hits, and opens the linked material.
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
memory-bank
Maintain and update project memory-bank files for persistent context across Claude Code sessions. Use when starting a new session, completing features, making architectural changes, or when context needs to be preserved. Triggers on: memory bank, project context, session start, context update, CLAUDE.md, project…
dag-context-bridger
Manages context passing between DAG nodes and spawned agents. Handles context summarization, selective forwarding, and token budget optimization. Activate on 'bridge context', 'pass context', 'summarize context', 'context management', 'agent context'. NOT for execution (use dag-parallel-executor) or aggregation (use…
planning-with-files
Manus-style persistent markdown planning - use filesystem as working memory with taskplan.md, findings.md, and progress.md for complex multi-step tasks that survive context resets.