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 Firou91/dyslex.ai --skill context-reentrygit clone --depth 1 https://github.com/Firou91/dyslex.aiWrote 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/firou91/dyslex.ai/context-reentry)<a href="https://agentmods.dev/skills/firou91/dyslex.ai/context-reentry"><img src="https://agentmods.dev/badge/skills/firou91/dyslex.ai/context-reentry.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 5.1 | $0.00036 | $0.00486 |
| Opus 5 | $0.00018 | $0.00243 |
| Sonnet 5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
context-reentry 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Reentry
Superpowers Gate
Before applying this skill, verify that Superpowers is available in the current session, such as an active superpowers: skill, using-superpowers, or equivalent Superpowers workflow instructions.
If Superpowers is missing or uncertain, stop and reply exactly with this guidance before doing any dyslex.ai work:
dyslex.ai requires Superpowers before it can run. Install Superpowers from /plugins, or use codex plugin add superpowers@<marketplace> if you manage plugins from the Codex CLI, then start a new session.
Do not perform the requested dyslex.ai workflow until Superpowers is installed and loaded.
Create a reliable reentry point. Do not invent missing decisions.
Functional Mechanism
Primary dimensions: workingMemory.contextRetentionLoad, workingMemory.simultaneousInformationLoad, executiveFunction.planningLoad, and executiveFunction.sequencingLoad.
Use the agent's memory of the conversation as external state so the user does not need to mentally reconstruct the whole task.
Interaction Risk
After a pause, compaction, interruption, or task switch, the user may lose decisions, constraints, branch state, test results, or the next safe action.
Agent Strategy
- Separate known facts from unknowns.
- Keep
completed,remaining, andnext single actiondistinct. - Preserve exact branches, versions, paths, commands, errors, and decisions.
- Mention only the context needed to resume safely.
Avoid
- Do not invent missing decisions.
- Do not infer a diagnosis from context loss.
- Do not overwhelm the user with the full transcript when a short reentry point is enough.
- Do not ask the user to restate information already available in context.
Output Format
Where we are
Already decided
Completed
Remaining
Next single action
Important context
Rules
- Use only information present in the conversation, files, plan, or tool output.
- Mark unknown items as unknown.
- Keep the next action small and concrete.
- Preserve exact file names, commands, branches, issue IDs, and errors.
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.
- 3d ago Changed · +24 lines 980617793aa4
- 7d ago First seen · 39 lines · 36 tokens per session scan A 83a456febfba
context-reentry is a skill published in the GitHub repository Firou91/dyslex.ai (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 486 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…