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/simonrowland/goal-flight/resumegit clone --depth 1 https://github.com/simonrowland/goal-flightWrote 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/simonrowland/goal-flight/resume)<a href="https://agentmods.dev/commands/simonrowland/goal-flight/resume"><img src="https://agentmods.dev/badge/commands/simonrowland/goal-flight/resume.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 | $0.00022 | $0.01415 |
| Opus 5 | $0.00011 | $0.00707 |
| Sonnet 5 | $0.00004 | $0.00283 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
resume 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
resume
Rebuild working context from files and procedural status.
Applies only when Goal Flight was already in play (see protocols/state-handoff.md).
Read and run protocols/session-preflight.md as the controller-start hook before
rebuilding status.
STEP 0 — Load the skill body FIRST (unconditional; do not skip)
Before running any step below, read the repository SKILL.md end-to-end, plus
the protocols it references for the work you are about to do. This is not optional
and not compaction-only:
/goal-flight resumemay load only this command body, not the full skill.- After a compaction the
SKILL.mdalready in your context is frequently STALE or truncated: system reminders silently drop load-bearing rules across compactions. - Resuming from RESUME-NOTES + the resume args + your own judgment, WITHOUT the
loaded skill body, is the documented failure mode. Controllers then improvise the
practice instead of following it and drift into the known anti-patterns:
- the host Agent/Task tool as a code executor instead of
goalflight_dispatch.py; - engagement-question boxes over obvious matters ("I found a problem: fix it?" — the forbidden "are-you-still-there" pattern); just act, per §Autonomous throughput;
spawn_taskchips for findings a worker could do autonomously, instead of queue-backlog worker tasks.
- the host Agent/Task tool as a code executor instead of
Self-test: if you cannot quote SKILL.md's Hard Invariants and Dispatch Model
from what is currently loaded, you have NOT loaded it.
- Native (Claude Code): the body loads on
/goal-flight. Confirm it is present and fresh by quoting one Hard Invariant; if you cannot, re-invoke/goal-flight. - Non-native hosts (codex / grok / cursor / opencode): read your installed host
wrapper, then
<skill-root>/SKILL.mdend-to-end from disk.
Do not act on any resume state until STEP 0 is satisfied.
STEP 1 — Reload order + handoff
Follow AGENTS.md, then the canonical post-compaction reload order in SKILL.md
and protocols/state-handoff.md: session-status verdict, SKILL.md end-to-end,
named controller registration from protocols/session-preflight.md, store
baseline, handoff prose, status, next, then continue the top task without
waiting for a re-prompt when no real blocker exists.
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 Changed · +2 lines · +10 tokens per session 52b88436d3f7
- yesterday Changed · +50 lines 14da3d49abb1
- 5d ago First seen · 76 lines · 12 tokens per session scan A b773e61f4eb7
resume is a command published in the GitHub repository simonrowland/goal-flight (20 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,415 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 2026-08-30.
Other commands, from other repositories
review-context7-updates
Please read the @README.md and @docs/tools/package-documentation.md to understand the high level context of my repo.
mine
Quickly capture relevant project context into Memento memory.
help
Show comprehensive Memento help — available MCP tools and usage patterns.
init
Set up Memento — configure MCP server and verify everything works.
search
Search your memories using Memento hybrid retrieval.
status
Show Memento server status and current configuration.