/sdlc-log
Show what LoopSmith is doing right now — which goal, which thread, and its recent action history — from the local action log alone, no live agent inspection needed. Use when the user runs /sdlc-log or asks what the loop/agent is doing right now, on which goal or thread, or wants
$ npx -y skills add swapnil-agrim/loopsmith --skill sdlc-log --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/sdlc-log
Context preview
The summary Claude sees to decide when to auto-load this skill.
Show what LoopSmith is doing right now — which goal, which thread, and its recent action history — from the local action log alone, no live agent inspection needed. Use when the user runs /sdlc-log or asks what the loop/agent is doing right now, on which goal or thread, or wants
SKILL.md
sdlc-log.SKILL.mdname: sdlc-log
description: Show what LoopSmith is doing right now — which goal, which thread, and its recent action history — from the local action log alone, no live agent inspection needed. Use when the user runs /sdlc-log or asks what the loop/agent is doing right now, on which goal or thread, or wants the status of a specific in-flight goal.
allowed-tools: Bash(python3 *)
sdlc-log
Read side of the **local-only action log** (`skills/sdlc-loop/scripts/actionlog.py` writes it, opt-in via config `action_log.enabled`, default `false`) — a full-granularity trace of file touches, model/effort choices, subagent dispatch, and every mechanically-guaranteed loop action (claim/worktree/verify/gate/record), kept entirely separate from the team ledger and never committed (`.sdlc/state/log/`, already gitignored via the existing `RUNTIME_IGNORES` mechanism). This skill only ever READS `.sdlc/state/log/*.jsonl`; it shares no code with the writer.
For **"where are we right now"**, run `python3 "${CLAUDE_SKILL_DIR}/scripts/log.py" status .sdlc` and relay the output. It lists every ACTIVE goal (claimed, and not yet recorded done/parked/failed), newest activity first, one line per `(goal, thread)` with its most recent action and how long ago it happened. A goal that has been quiet a long time (`claimed, last activity 3h ago`) is a visible smell for a human to judge — this tool makes no liveness claim of its own; it only reports what the log itself says.
For **"what's the status on THIS goal"** — especially a large, multi-thread one (parallel slices, several subagent dispatches) — run `python3 "${CLAUDE_SKILL_DIR}/scripts/log.py" goal .sdlc <goal>` and relay the full, oldest-first history for that one goal, `[actor,thread]`-prefixed, with the distinct thread count in the header.
If either command reports no entries, the feature is very likely just **off** — point the user at config `action_log.enabled: true` (default `false`, matching every other opt-in feature in this kit) rather than treating it as an error. This skill needs no `gh`, no network access, and spends no LLM tokens beyond relaying its own plain-text output.
Read more
name: sdlc-log description: Show what LoopSmith is doing right now — which goal, which thread, and its recent action history — from the local action log alone, no live agent inspection needed. Use when the user runs /sdlc-log or asks what the loop/agent is doing right now, on which goal or thread, or wants the status of a specific in-flight goal. allowed-tools: Bash(python3 *)
sdlc-log
Read side of the **local-only action log** (`skills/sdlc-loop/scripts/actionlog.py` writes it, opt-in via config `action_log.enabled`, default `false`) — a full-granularity trace of file touches, model/effort choices, subagent dispatch, and every mechanically-guaranteed loop action (claim/worktree/verify/gate/record), kept entirely separate from the team ledger and never committed (`.sdlc/state/log/`, already gitignored via the existing `RUNTIME_IGNORES` mechanism). This skill only ever READS `.sdlc/state/log/*.jsonl`; it shares no code with the writer.
For **"where are we right now"**, run `python3 "${CLAUDE_SKILL_DIR}/scripts/log.py" status .sdlc` and relay the output. It lists every ACTIVE goal (claimed, and not yet recorded done/parked/failed), newest activity first, one line per `(goal, thread)` with its most recent action and how long ago it happened. A goal that has been quiet a long time (`claimed, last activity 3h ago`) is a visible smell for a human to judge — this tool makes no liveness claim of its own; it only reports what the log itself says.
For **"what's the status on THIS goal"** — especially a large, multi-thread one (parallel slices, several subagent dispatches) — run `python3 "${CLAUDE_SKILL_DIR}/scripts/log.py" goal .sdlc <goal>` and relay the full, oldest-first history for that one goal, `[actor,thread]`-prefixed, with the distinct thread count in the header.
If either command reports no entries, the feature is very likely just **off** — point the user at config `action_log.enabled: true` (default `false`, matching every other opt-in feature in this kit) rather than treating it as an error. This skill needs no `gh`, no network access, and spends no LLM tokens beyond relaying its own plain-text output.
Guardrails + an overnight autopilot for your AI coding agent — one that plans before it codes, won't ship work that fights your strategy, and gets sharper every run.
Other skills on loopsmith.
- /sdlc-align
Periodic cumulative-drift audit — look at the last stretch of shipped goals as a whole and ask whether the work still matches the north-star's stated bets, or whether the strategy has been quietly rewritten by accumulation. Use when the user runs /sdlc-align, when /sdlc-status
Open skill - /sdlc-brainstorm
The Goal phase — turn an idea into an approved design before any code: explore intent, requirements, and constraints; ask one question at a time; propose 2-3 approaches with trade-offs; restate as one concrete, checkable goal. Use at Goal, or when the user runs /sdlc-brainstorm.
Open skill - /sdlc-context
Pre-flight recall — assemble a compact, cited "context brief" of prior art (knowledge graph + past issues + conventions) for a goal before running it, so a crucial earlier finding is never missed just because the context window flushed. Use at the start of a goal when the
Open skill - /sdlc-contract-check
Detect breaking changes to public APIs, event shapes, exported types, CLI flags, or env vars before consumers hit them. Triggers on "breaking change", "API change", "contract", "consumers", "exported type", "event shape", "route change". A conditional-risk review orthogonal to
Open skill - /sdlc-debug
Diagnose a bug hypothesis-first, reproduce-as-a-test-first — before writing any fix. Triggers on "bug", "broken", "not working", "error", "exception", "investigate", "why is X". A conditional-risk skill orthogonal to sdlc-review; always LoopSmith's own (no companion equivalent).
Open skill - /sdlc-decide
Record an architectural decision as a machine-checkable invariant so an edit that breaks it is DENIED, not just discouraged. Use when the user runs /sdlc-decide, says "make this a rule / an invariant", "enforce this", "stop us breaking X", or after a retrospective proposes a
Open skill