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 HECer/yoke --skill maintaining-contextgit clone --depth 1 https://github.com/HECer/yokeWrote 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/hecer/yoke/maintaining-context)<a href="https://agentmods.dev/skills/hecer/yoke/maintaining-context"><img src="https://agentmods.dev/badge/skills/hecer/yoke/maintaining-context/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/hecer/yoke/maintaining-context"><img src="https://agentmods.dev/badge/skills/hecer/yoke/maintaining-context.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 | $0.00057 | $0.00407 |
| Opus 5.5 | $0.00023 | $0.00163 |
| Sonnet 5.5 | $0.00011 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
maintaining-context 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 1mo 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.
What it actually says
Maintaining Project Context
Yoke keeps durable, cross-session context in .yoke/context/. These files are the
project's memory — they survive between sessions and loop iterations, so an agent
starting with a fresh context window is never blind.
Before substantial work
- Read
.yoke/context/PROJECT.md— the north star (goal, constraints, non-goals, success criteria). Align your work to it. If the task contradicts a non-goal, stop and flag it. - Skim
.yoke/context/KNOWLEDGE.mdfor gotchas that affect what you are about to do.
While working
-
When you make a non-obvious decision (a trade-off, an architectural choice, a rejected alternative), append it to
.yoke/context/DECISIONS.md:## <YYYY-MM-DD> — <area-or-story>: <short title> What you chose and why, in one or two lines.(This mirrors the heading the loop writes for completed stories, so loop-authored and hand-authored entries share one shape.)
-
When you learn a reusable fact or gotcha (a non-obvious build step, an API quirk, a convention), append a bullet to
.yoke/context/KNOWLEDGE.md.
Rules
- Never rewrite history in
DECISIONS.md— only append. - Keep
PROJECT.mdcurated and short; it is read into every loop prompt. - Inside the autonomous loop, the loop appends a decision per completed story for you — you still add the why and any learnings.
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.
- 1mo ago First seen · 35 lines · 57 tokens per session scan A 8060bae3c189
maintaining-context is a skill published in the GitHub repository HECer/yoke (2 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 407 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
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
post-cutoff
What THIS TEAM has adopted or ruled on that postdates your training cutoff — a small, human-curated set, not a watchlist. Read BEFORE choosing an approach, picking a model, designing a classifier/router/gate, or evaluating a vendor. Also the procedure for proposing and retiring entries. Individual briefs ship as their…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
ox
SageOx team context and session recording for AI coworkers. Use when working in a repository that has .sageox/ initialized, when you need team conventions, or when recording coding sessions to a shared ledger.
ox-cli-consult
Search SageOx team memory BEFORE answering from first-principles reasoning. Auto-fire when the user references recent or specific work or asks a before/after question: "I just pushed...", "did X fix Y?", "is the alert gone now?", "this request", or anything tied to a prior decision, a prod anomaly, or a metric/cost…
ox-cli-prime
Load SageOx team context for this AI coworker session.