# Ase Task Edit > > - **Type:** Skill - **Install:** `agentstack add skill-rse-ase-ase-task-edit` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [rse](https://agentstack.voostack.com/s/rse) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [rse](https://github.com/rse) - **Source:** https://github.com/rse/ase/tree/master/plugin/skills/ase-task-edit - **Website:** https://ase.tools ## Install ```sh agentstack add skill-rse-ase-ase-task-edit ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md Iteratively Edit a Task Plan $ARGUMENTS Establish and refine the *task plan* purely through a *chat-driven loop*. The user steers each round via an interactive dialog that offers continued refinement, finalization, or hand-off to implementation or preflight. @${CLAUDE_SKILL_DIR}/../../meta/ase-format-task.md Procedure --------- Treat the as a *refinement instruction* for the plan, and update in-place by *applying* the requested to the *plan*. When refining the plan this way, preserve the overall structure of the plan and only modify what the user actually requested. Do *not* rewrite unrelated sections of the plan. Calculate the number of words of . Set true. Create a new plan from scratch and store the result as by closely following the defined plan format and injecting into it all the information from the and all decisions you derived from the . If a `CHANGELOG.md` file exists in the project (or in any affected sub-package), the plan *MUST* include, as part of its `## CHANGES` section, an explicit bullet point describing the addition of a corresponding new entry to that `CHANGELOG.md` file, aligned with its existing style and conventions. is equal `true`"> You *MUST* completely omit the `## VERIFICATION` section (including its heading and all of its bullet points) from . Call the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the `ase` MCP server and use the `text` field of its response for fresh and information. Then insert the current , , and information and calculate the number of words of . Set true. 1. **Determine Task and Instruction:** 1. Set initially. Inherit the always existing from the current context. Inherit the always existing from the current context. Do not output anything. 2. React on task and/or instruction: 1. matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$` "> Set (set task id to instruction) and (set instruction empty), call the `ase_task_id(id: "", session: "")` tool from the `ase` MCP server to switch the task, and then only output the following : ⧉ **ASE**: ◉ task: ****, ▶ status: **task given** 2. has the format `: ` where matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$` and is *empty* "> Set (set instruction to empty) and (set task id to id) and call the `ase_task_id(id: "", session: "")` tool from the `ase` MCP server to switch the task, and then only output the following : ⧉ **ASE**: ◉ task: ****, ▶ status: **task given** 3. has the format `: ` where matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$` and is *not empty* "> Set (set instruction to text) and (set task id to id) and call the `ase_task_id(id: "", session: "")` tool from the `ase` MCP server to switch the task, and then only output the following : ⧉ **ASE**: ◉ task: ****, ▶ status: **task given** ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** 4. is not empty "> Only output the following : ⧉ **ASE**: ◉ task: ****, ▶ status: **task inherited** ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** 5. is empty "> Only output the following : ⧉ **ASE**: ◉ task: ****, ▶ status: **task inherited** 2. **Determine Plan:** 1. Determine any existing plan content: is equal `true` *and* a `ase_task_save(id: '', ...)` tool call exists earlier in the current session "> Set to the `text` argument of the most recent `ase_task_save(id: '', ...)` tool call, *without* calling `ase_task_load` again. Set plan reused. Do not output anything. Call the `ase_task_load(id: "")` tool of the `ase` MCP server to load any existing plan content and set to the `text` output field of this `ase_task_load` tool call. Do not output anything related to this MCP tool call. Set plan loaded. Set false. - If starts with `ERROR:`: Silently ignore the MCP error. Set to empty. Set to "0". Do not output anything. - If starts NOT with `ERROR:`: Set (set content to text). Calculate the number of words of . Only output the following : ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **** 2. is empty AND is empty"> Ask the user interactively, without a special tool, for the initial plan content with a single question: `**No plan content yet. What is the task you want to plan?**` Then set to the response of the user and only output the following : ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** 3. is not empty AND is not empty AND is not equal "> *Determine previous-plan handling*: - If matches the regex `^(OVERWRITE|REFINE|PRESERVE)$`: Honor the pre-selection what to do with the previous plan. Set . - If is equal to `none`: In the following, you *MUST* *NOT* use your built-in tool! Instead, you *MUST* just show a custom dialog according to the expanded `custom-dialog` definition. You *MUST* closely follow this definition: Previous Plan: Should the previous plan content be overwritten, refined, or preserved? OVERWRITE: Continue operation, overwrite previous plan. REFINE: Continue operation, refine previous plan. PRESERVE: Cancel operation, preserve previous plan. Check the tool and dispatch accordingly: - If is `CANCEL` or `PRESERVE`: Only output the following and then immediately *STOP* processing this skill: ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan preserved** - If is `OVERWRITE`: Only output the following and continue processing: ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan overwritten** ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** - If is `REFINE`: Only output the following and continue processing: ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan refined** ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** - If matches `OTHER: `: Set (append the user's free-text hint to the existing instruction). Only output the following and continue processing: ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan refined** ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** 4. matches the case-insensitive regex `^\s*#+\s*TASK\b` AND is empty"> Set (set instruction to content). Set (set content to empty). Set true. Do not output anything. 5. is empty AND is not empty"> Only output the following and continue processing: ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **instruction given** ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan generated** 3. **Iterative Plan Refinement Loop:** *REPEAT* the following steps from 3.1 up to and including 3.4 in a *LOOP* until the user selects `DONE`, `GRILL`, `IMPLEMENT`, or `PREFLIGHT`, or declines/cancels in the dialog of step 3.4: 1. *Update timestamp*: contains '⚙ Modified:' AND is 'true'"> Update with the current time in ISO-style format, which has to be determined by calling the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the `ase` MCP server and use the `text` field of its response. Update the `⚙ Modified: ...` line of with the new `⚙ Modified: `. Do not output anything. 2. *Persist plan*: is 'true'"> Call the `ase_task_save(id: "", text: "")` tool of the `ase` MCP server to persist the current plan, and then set false again. Calculate the number of words of . Do not output anything related to this MCP tool call except the following : ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan saved** 3. *Render plan*: Treat as *verbatim* Markdown. Only output the following , so the user can read the plan and react to it. If is longer than 90 lines and a `## IMPLEMENTATION DRAFT` section (from the companion skill `ase-task-preflight`) exists, replace the entire content of the `## IMPLEMENTATION DRAFT` section with `[...]`. Else, do *not* truncate, summarize, or partially show the plan. Use the following : 4. *Determine next step*: - If is not equal to `none`: Treat as a comma-separated chronological list of pre-selected next-step tokens. *Split* it on `,`, take the *first* token as , and store the remaining tokens (joined back with `,`, or `none` if empty) into so subsequent loop iterations or downstream skills can consume the tail. - If matches the regex `^(DONE|GRILL|IMPLEMENT|PREFLIGHT)$`: Honor the pre-selected token. Set . Set (clear the instruction, as any instruction carried in via the arguments was already applied to the plan in step 2 before this loop), so that a later `OTHER: ` refinement correctly starts from a *fresh* refinement instruction below. - else: Only output the following and then immediately *STOP* processing the entire current skill: ⧉ **ASE**: ☻ skill: **ase-task-edit**, ▶ ERROR: invalid `--next` token: **** - If is equal to `none`: In the following, you *MUST* *NOT* use your built-in tool! Instead, you *MUST* just show a custom dialog according to the expanded `custom-dialog` definition. You *MUST* closely follow this definition: Next Step: How would you like to proceed with the plan? DONE: Mark plan finalized, exit planning loop. GRILL: Hand off plan to grilling. PREFLIGHT: Hand off plan to pre-flighting. IMPLEMENT: Hand off plan to implementation. Check the tool and dispatch accordingly: - If is `DONE`: *Break* out of the *loop*, only output the following and then *STOP*. Do *not* implement the plan. ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan finalized -- done** - If is `GRILL`: *Break* out of the *loop*. Set (set args to empty). Set --int-reuse-task. is not equal `none`"> Set --next Only output the following and then call the `Skill(skill: "ase:ase-task-grill", args: "")` tool to *grill* the finalized plan. ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan finalized -- hand-off to grilling** - If is `PREFLIGHT`: *Break* out of the *loop*. Set (set args to empty). Set --int-reuse-task. is not equal `none`"> Set --next Only output the following and then call the `Skill(skill: "ase:ase-task-preflight", args: "")` tool to *apply* the finalized plan. ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan finalized -- hand-off to pre-flight** - If is `IMPLEMENT`: *Break* out of the *loop*. Set (set args to empty). Set --int-reuse-task. is not equal `none`"> Set --next Only output the following and then call the `Skill(skill: "ase:ase-task-implement", args: "")` tool to *apply* the finalized plan. ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan finalized -- hand-off to implementation** - If matches `OTHER: `: Set (replace existing instruction). Finally, only output the following and then *continue* the *loop* at step **3.1**! ⧉ **ASE**: ◉ task: ****, ⇌ instruction: ****, ▶ status: **plan refined** - If is `CANCEL`: *Break* out of the *loop*, only output the following and then *STOP*. Do *not* implement the plan. ⧉ **ASE**: ◉ task: ****, ✪ plan: **** words, ▶ status: **plan refinement cancelled** ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [rse](https://github.com/rse) - **Source:** [rse/ase](https://github.com/rse/ase) - **License:** Apache-2.0 - **Homepage:** https://ase.tools Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-rse-ase-ase-task-edit - Seller: https://agentstack.voostack.com/s/rse - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.