From 6d0fb5332501d7df5a7ed8298b7decfd772266ae Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Mon, 26 Oct 2026 03:12:33 +0000 Subject: [PATCH] fix: restore transcript lookup sentences Reflect resolves the directory through the Codex adapter and selects jsonl by type and payload. The other skills keep the upstream path sentences. Co-authored-by: Kaitian Xie --- .agents/skills/automate-me/SKILL.md | 2 +- .agents/skills/poteto-mode/playbooks/eval.md | 2 +- .agents/skills/poteto-mode/playbooks/session-pickup.md | 2 +- .agents/skills/recall/SKILL.md | 2 +- .agents/skills/reflect/SKILL.md | 6 +++--- .agents/skills/show-me-your-work/SKILL.md | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/.agents/skills/automate-me/SKILL.md b/.agents/skills/automate-me/SKILL.md index 63d830b..e72d52c 100644 --- a/.agents/skills/automate-me/SKILL.md +++ b/.agents/skills/automate-me/SKILL.md @@ -27,7 +27,7 @@ Update mode changes the rest of the flow: ### 1. Mine their history -Locate the active workspace's transcripts before fanning out. Use the adapter's workspace-filtered history discovery; do not assume the system prompt names a transcript directory. Filter Codex session metadata by workspace before reading any transcript body. +Locate the active workspace's transcripts before fanning out. The system prompt names the workspace's `agent-transcripts/` directory. Use only that path. Don't glob across `~/.cursor/projects/*/`. That crosses workspace boundaries and reads private chats from unrelated projects. Survey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill. Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting: diff --git a/.agents/skills/poteto-mode/playbooks/eval.md b/.agents/skills/poteto-mode/playbooks/eval.md index f6d6741..768a894 100644 --- a/.agents/skills/poteto-mode/playbooks/eval.md +++ b/.agents/skills/poteto-mode/playbooks/eval.md @@ -19,7 +19,7 @@ 3. **Author one organic prompt.** What a user would type. No leakage of what's being measured. 4. **Spawn N parallel candidates** on different models per the **arena** skill's Phase B. Each works in its own sanitized dir. Same prompt to each. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. 5. **Spawn one blinded judge** on a different model family per the **arena** skill's Phase C. Judge sees outputs by sanitized label and the rubric, never a model name. -6. **Verify the chain from transcripts, not self-report.** Read each candidate's local transcript under the active workspace's Codex history selected through the adapter. Filter Codex session metadata by workspace before reading any transcript body. Look at which files each candidate actually opened. Grade chain-following from the files it really read plus the shape of the code, never from the candidate's own claims. +6. **Verify the chain from transcripts, not self-report.** Read each candidate's local transcript under the active workspace's `agent-transcripts/` directory (the system prompt names this path). Do not glob across `~/.cursor/projects/*/`. That crosses workspace boundaries and reads private chats from unrelated projects. Look at which files each candidate actually opened. Grade chain-following from the files it really read plus the shape of the code, never from the candidate's own claims. 7. **Read every candidate output yourself** end to end. Compare to the judge's verdict. Disagreement means a model is biased or the rubric is ambiguous. Synthesize. **Reply:** variant under test, rubric, per-candidate notes, judge's verdict, your synthesis, and a recommendation for whether to promote the variant. diff --git a/.agents/skills/poteto-mode/playbooks/session-pickup.md b/.agents/skills/poteto-mode/playbooks/session-pickup.md index d5ef22d..876b143 100644 --- a/.agents/skills/poteto-mode/playbooks/session-pickup.md +++ b/.agents/skills/poteto-mode/playbooks/session-pickup.md @@ -2,7 +2,7 @@ **You own the resume point. Read the prior trail, don't redo it.** -1. Locate the prior trail. A local transcript under the active workspace's Codex history selected through the adapter (filter session metadata by workspace before reading any conversation body), a cloud-agent URL, or a pushed branch. Read the metadata overview and last messages first, then scan back for the decision points. Parse a long transcript in a subagent and keep the reduced timeline in the main thread (the **principle-guard-the-context-window** skill). Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. +1. Locate the prior trail. A local transcript under the active workspace's `agent-transcripts/` directory (the system prompt names the path. Do not glob across `~/.cursor/projects/*/`, that crosses workspace boundaries and reads private chats from unrelated projects), a cloud-agent URL, or a pushed branch. Read the metadata overview and last messages first, then scan back for the decision points. Parse a long transcript in a subagent and keep the reduced timeline in the main thread (the **principle-guard-the-context-window** skill). Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. 2. Reconstruct operational state. The branch and worktree, what already landed (`git log`, `git diff` against the base), the open todos, the decisions made. The prior trail is authoritative input. Resist the bias to re-derive it. 3. Diff done vs pending. Compare what shipped against what was planned, name the resume point, do not re-run the prior repro or redo completed work. A "let me verify from scratch" pass means you're treating the trail as untrustworthy when it's authoritative. 4. Route the remaining work to the matching playbook and pick the verdict: continue the execution, ship a finished recommendation, ratify or override a prior conclusion, or postmortem a failed run. The pickup playbook ends here. The routed playbook owns the rest. diff --git a/.agents/skills/recall/SKILL.md b/.agents/skills/recall/SKILL.md index 0c4fbdf..83b0aae 100644 --- a/.agents/skills/recall/SKILL.md +++ b/.agents/skills/recall/SKILL.md @@ -13,7 +13,7 @@ Keep it tight and on-topic. Read only what the in-scope threads need, then stop. Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the **why** skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone. -Find Codex history through the adapter's workspace-scoped history rules. JSONL rollouts contain typed events, including session metadata and tool activity; a line is not necessarily a chat message. +Transcripts live at `~/.cursor/projects//agent-transcripts//.jsonl`, where `` is the workspace path with the leading slash dropped and each "/" turned into "-" (so `/Users/you/proj` becomes `Users-you-proj`). Every line is one chat message. 1. Classify, then route. One specific prior chat to resume is the `session-pickup` playbook, not this. Turning habits into a durable skill is `automate-me`. A human-readable summary of your work is a different task. Recall loads working context across recent chats before you act. If the user already gave you a full state capsule (paths, branch, the change), use it and skip the mining. 2. Lock the scope before searching. Pin the window ("recent" is a real range, default the last 7 days), the topic if named, and the workspace (default the active one. Never read another project's transcripts without being asked). State the scope back. Never quietly turn "all" into "recent N". diff --git a/.agents/skills/reflect/SKILL.md b/.agents/skills/reflect/SKILL.md index 956ed1d..1238248 100644 --- a/.agents/skills/reflect/SKILL.md +++ b/.agents/skills/reflect/SKILL.md @@ -13,13 +13,13 @@ Invoke when the user says "reflect" or "/reflect". Skip when the conversation is ## 1. Locate the active transcript -Before fanning out, find this conversation's transcript in the workspace-scoped Codex history described by the adapter. Filter Codex session metadata by workspace before reading any transcript body. +Before fanning out, find this conversation's transcript in the `agent-transcripts/` directory the system prompt names. Do not glob across `~/.cursor/projects/*/`. That crosses workspace boundaries and reads private chats from unrelated projects. Resolve the directory the way `../poteto-mode/references/codex.md` describes; do not read `~/.cursor/projects/`. ```bash -ls -t /*.jsonl /*/*.jsonl /*/subagents/*.jsonl 2>/dev/null | head -10 +ls -t /*.jsonl /*/*.jsonl /*/subagents/*.jsonl 2>/dev/null | head -10 ``` -That covers the legacy flat (`.jsonl`), current nested (`/.jsonl`), and subagent (`/subagents/.jsonl`) layouts. For each candidate, read the first JSONL line. Take the file whose `message.content[0].text` contains the conversation's opening user prompt. If none matches, pass a tight digest of the session instead. +That covers the legacy flat (`.jsonl`), current nested (`/.jsonl`), and subagent (`/subagents/.jsonl`) layouts. For each candidate, decode `type` and `payload` rather than reading `message.content[0].text`. Take the file whose payload contains the conversation's opening user prompt. If none matches, pass a tight digest of the session instead. ## 2. Spawn three reviewers in parallel diff --git a/.agents/skills/show-me-your-work/SKILL.md b/.agents/skills/show-me-your-work/SKILL.md index 83c1b34..31939a4 100644 --- a/.agents/skills/show-me-your-work/SKILL.md +++ b/.agents/skills/show-me-your-work/SKILL.md @@ -55,7 +55,7 @@ Commit it only when the work is ambitious enough that a reviewer needs the trail ## Audit the log against the transcript -At the end of the run, before handing back, check the log told the truth. Read this run's transcript under the active workspace's Codex history selected through the adapter. Keep the scan scoped to this workspace; do not read unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's `start` rows, or at the first row if this run created the log, and ends at the next `start` row of another run: +At the end of the run, before handing back, check the log told the truth. Read this run's transcript under the active workspace's `agent-transcripts/` directory (the system prompt names the path). Don't glob across `~/.cursor/projects/*/`. That reads unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's `start` rows, or at the first row if this run created the log, and ends at the next `start` row of another run: - Check that every row maps to a real decision or action. - Check that each row's evidence resolves and shows what the row claims.