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/suuus/ape-context/context-distillnpx skills add suuus/ape-context --skill context-distillgit clone --depth 1 https://github.com/suuus/ape-contextWrote 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/suuus/ape-context/context-distill)<a href="https://agentmods.dev/skills/suuus/ape-context/context-distill"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-distill.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 | $0.00017 | $0.01920 |
| Opus 5 | $0.00009 | $0.00960 |
| Sonnet 5 | $0.00003 | $0.00384 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
context-distill 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 5d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze the user's Copilot session history and the documentation sources discovered in Phase 3 (Docs) to extract actionable intent and constraints that flow into Phase 9 (Instructions).
This is the Intent layer of the ISEE framework — turning implicit organisational knowledge into explicit, machine-readable guardrails. It uses two complementary signals: what the team documents (docs) and what the team actually does (history).
Process
0. Analyze session history
Invoke skill: context-history
Before reading any documentation, analyze the user's Copilot session history. This surfaces behavioural patterns — recurring tasks, file hotspots, cross-repo topology, workflow chains — that reveal implicit intent. History-based observations are presented to the user for confirmation before proceeding.
If history consent is denied or history returns empty:
- Tell the user: "Session history analysis was skipped — I'll work from your documentation sources instead."
- This is a valid choice, not a failure. Continue to step 1 normally.
- If doc sources are also unavailable (Phase 3 was skipped), the Fallback section at the end of this skill will activate.
1. Gather tagged sources from Phase 3
Review the doc sources discovered earlier, grouped by content tag:
[intent]— team priorities, values, strategy[constraint]— security policies, compliance rules, approval requirements[process]— ceremonies, workflows, decision flows, escalation paths[reference]— API specs, guides (lower priority for distillation)
Retrieve tagged sources from the session store:
SELECT value FROM session_state WHERE key = 'tagged_doc_sources';
If no state exists, check conversation context for Phase 3 output. If neither is available, inform the user: "No documentation sources found from Phase 3. Run /context-docs first, or I'll ask you directly about your team's intent."
2. Read and analyze documents
For each [intent], [constraint], and [process] source:
- Use the appropriate MCP server to read the content (e.g.,
workiqfor SharePoint,atlassian-jirafor Confluence, file tools for repo docs) - Extract statements that express:
- What the team values — priorities, quality bars, what "done" means
- What is not allowed — security boundaries, compliance rules, forbidden patterns
- What requires approval — deployment gates, merge policies, access escalation
- How work flows — ceremonies, handoff points, escalation paths
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.
- 5d ago First seen · 202 lines · 17 tokens per session scan A 063a28955c25
context-distill is a skill published in the GitHub repository suuus/ape-context (2 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 1,920 once invoked, about $0.0001 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…