M Go
Resume the last saved work session — read the standing handoff file `.m_last_task.md` (written by /m_save) at the project root, restore context by reading the key files it names, then continue from its recorded "next step". Use at the start of a fresh session to pick up exactly where the previous one stopped.
Install
$ agentstack add skill-mapuamap-denys-fast-mskills-m-go ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-mapuamap-denys-fast-mskills-m-go) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
m_go
Read .m_last_task.md from the project root (written earlier by /m_save), rebuild working context, and continue the work — not just summarize it.
Inputs
$ARGUMENTS(optional): adjustments to the resumed task ("skip the tests part", "focus on X first"). Apply them on top of the saved plan.
Procedure
- Read the snapshot. Read
.m_last_task.mdat the project root.
- Missing → tell the user there is no saved task (
/m_savehasn't been run here) and stop. - Present in a parent directory but not here → mention it and ask which project they meant; don't guess.
- Sanity-check freshness. Compare the snapshot's branch/commit line with
git branch --show-currentandgit log -1 --oneline. If the repo has moved on (different branch, new commits, dirty tree not explained by the snapshot), say so in one line and account for it — the snapshot describes intent, the repo describes reality; reality wins. - Restore context. Read every file under "Key files" (relevant parts, not blindly whole files). If the snapshot links an
.m_plan//run, open05_step_plan.mdand09_verification.md— for a plan run, prefer resuming via/m_plan_implement(it owns the step-walking andV-*bookkeeping) and say you're doing so. - Brief the user (short). 3–5 lines: the task, what's done, and the next step you're about to take. This is a status line, not a report — then keep going without waiting, unless "Blockers / open questions" contains something only the user can answer (ask exactly that, then proceed).
- Continue the work from "⏭ Next step", honoring "Decisions & context" (don't re-litigate settled decisions) and using "How to verify" to check your results.
- Keep the snapshot current. When the resumed task completes, or the user switches to something else mid-run, update
.m_last_task.mdaccordingly (an/m_save-style overwrite) so the file never describes stale work as pending.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mapuamap
- Source: mapuamap/denys-fast-mskills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.