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 bestagentkits/agency-skills --skill context-enginegit clone --depth 1 https://github.com/bestagentkits/agency-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/bestagentkits/agency-skills/context-engine)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/context-engine"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/context-engine/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/bestagentkits/agency-skills/context-engine"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/context-engine.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 | $0.00075 | $0.01035 |
| Opus 5 | $0.00037 | $0.00517 |
| Sonnet 5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
context-engine 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Context Engine
The memory layer for C-suite advisors. Every advisor skill loads this first. Context is what turns generic advice into specific insight.
Keywords
company context, context loading, context engine, company profile, advisor context, stale context, context refresh, privacy, anonymization
Load Protocol (Run at Start of Every C-Suite Session)
Step 1 — Check for context file: ~/.claude/company-context.md
- Exists → proceed to Step 2
- Missing → prompt: "Run /cs:setup to build your company context — it makes every advisor conversation significantly more useful."
Step 2 — Check staleness: Read Last updated field.
- < 90 days: Load and proceed.
- ≥ 90 days: Prompt: "Your context is [N] days old. Quick 15-min refresh (/cs:update), or continue with what I have?"
- If continue: load with
[STALE — last updated DATE]noted internally.
- If continue: load with
Step 3 — Parse into working memory. Always active:
- Company stage (pre-PMF / scaling / optimizing)
- Founder archetype (product / sales / technical / operator)
- Current #1 challenge
- Runway (as risk signal — never share externally)
- Team size
- Unfair advantage
- 12-month target
Context Quality Signals
| Condition | Confidence | Action |
|---|---|---|
| < 30 days, full interview | High | Use directly |
| 30–90 days, update done | Medium | Use, flag what may have changed |
| > 90 days | Low | Flag stale, prompt refresh |
| Key fields missing | Low | Ask in-session |
| No file | None | Prompt /cs:setup |
If Low: "My context is [stale/incomplete] — I'm assuming [X]. Correct me if I'm wrong."
Context Enrichment
During conversations, you'll learn things not in the file. Capture them.
Triggers: New number or timeline revealed, key person mentioned, priority shift, constraint surfaces.
Protocol:
- Note internally:
[CONTEXT UPDATE: {what was learned}] - At session end: "I picked up a few things to add to your context. Want me to update the file?"
- If yes: append to the relevant dimension, update timestamp.
What ships with it
2 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.
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.
- 9d ago First seen · 135 lines · 75 tokens per session scan A f1773d41d4ab
context-engine is a skill published in the GitHub repository bestagentkits/agency-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,035 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
bootstrap-agent-identity
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who…
coordinate-reasoning
AI internal coordination using stigmergic signals — managing information freshness in context and memory, decay rates for assumption staleness, and emergent coherent behavior from simple local protocols. Use during complex tasks where multiple sub-tasks must coordinate, when context has grown long and information…
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
agentmemory-agents
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
exposure-risk-quantification
FAIR-aligned exposure quantification: turns a pile of recon findings into a defensible 0-100 + A-F org risk score (Likelihood x Impact, three ownership-aware factors: exposure/threat/impact), an ownership + proof demotion cap so unproven or weakly-owned findings can't inflate the number, a $-denominated FAIR…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.