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 commands/everyone-needs-a-copilot/claude-copilot/continuegit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/commands/everyone-needs-a-copilot/claude-copilot/continue)<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/continue"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/continue.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 | $0.00000 | $0.03602 |
| Opus 5 | $0.00000 | $0.01801 |
| Sonnet 5 | $0.00000 | $0.00720 |
| Haiku 4.5 | $0.00000 | $0.00360 |
Grade A, and why
continue 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 today.
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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue Previous Work
Resume a conversation by loading context from Memory Copilot and Task Copilot.
Command Argument Handling
This command supports an optional stream name argument for resuming work on specific parallel streams:
Usage:
/continue- Interactive mode (check pause checkpoints, then resume main initiative or select from streams)/continue Stream-B- Resume work on specific stream directly
Step 0: Check for Paused Tasks (Priority Check)
Before generic paused-task discovery, when a Task Copilot task ID is known or selected, ask the journey authority for its exact continuation:
cc journey resume --task <N> --json
# Add --run <run-id> when the response requires disambiguation.
If it returns an active journey, dispatch only its exact next_specialist using
the returned prepared agent_prompt_fragment at byte 0 of the Agent prompt.
Assemble the complete prompt and bind its exact SHA-256 with cc journey bind-prompt before dispatch, exactly as /protocol requires.
Do not rerun flow detection, choose another specialist, reconstruct Knowledge,
or treat a prepared envelope as dispatched. If it returns stored completion
evidence, perform no Agent dispatch. If it reports no journey, continue with the
generic paused-task behavior below. Invalid, ambiguous, drifted, or malformed
journey state fails closed and must not fall through to an optimistic generic
resume. Dispatch receipts mean observed/authorized only, not successful agent
completion.
BEFORE loading standard context, check for paused tasks:
tc task list --status paused --json
If paused tasks found, present resume options:
## Paused Work Detected
Found N paused task(s) from recent session:
1. <task title>
Paused reason: <from task metadata.pauseReason if set>
2. <task title>
...
Options:
[1-N] Resume specific paused task
[c] Continue with standard resume (ignore paused work)
[s] Show all streams
Select option:
User selections:
- Number (1-N): Set the chosen task back to in_progress and begin work:
tc task update <id> --status in_progress --json c: Proceed to standard resume flow (Step 1 below)s: Proceed to stream selection flow (Step 1 below, then stream list)
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.
- today First seen · 470 lines · 0 tokens per session scan A 5cec14f382c2
continue is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,602 tokens. 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 2026-09-04.
Other commands, from other repositories
gohm
Persona: You are the Knowledge Harvester -- you extract signal from noise, turning session work into durable organizational memory. Reflection Protocol: See agents/reflection-protocol.md for reflection requirements.
memory
You are the Memory Curator, the guardian of NASAB Pillar 5: Permanent Memory. You ensure that nothing is ever deleted from the knowledge base - only the retrieval path changes. You are the librarian of an infinite library where every book remains on the shelf, but some are easier to find than others.
context
You are the Context Manager, responsible for monitoring and optimizing context usage during long implementation sessions. You help prevent context overflow and maintain efficiency.
recall
/recall "query" Search and show compact index /recall "query" --type=decision Filter by entry type /recall "query" --min-weight=0.7 Filter by minimum weight /recall "query" --since=7d Filter by recency /recall "query" --tags=auth,security Filter by tags /recall --preview id1,id2,id3 Show content summaries for specific…
evolve
/evolve Pull lessons and evolve agents /evolve --dry-run Show what would change /evolve --commit Evolve and auto-commit /evolve --status Show evolution statistics.
INFO
Каждый новый терминал = новая сессия = пустой контекст. Агент не знает по какому проекту работаем, какой стек, какие серверы, где деплой, какие активные задачи. Пользователь вынужден на каждом старте перечислять одно и то же — теряется время и мысль.