@standardagents/skill 0.45.0 → 0.45.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +16 -13
  2. package/package.json +1 -1
  3. package/skills/agentbuilder/SKILL.md +33 -7
package/README.md CHANGED
@@ -29,20 +29,23 @@ Recommended:
29
29
  npx @standardagents/cli skill
30
30
  ```
31
31
 
32
- This opens an interactive picker and installs the bundled `agentbuilder`
33
- guidance into a supported coding agent. Currently:
32
+ This opens an interactive picker and installs the bundled `agentbuilder` skill
33
+ as an [Agent Skills](https://agentskills.io) folder. Every target gets the same
34
+ `agentbuilder/SKILL.md`:
34
35
 
35
- - Codex gets a skill folder in `$CODEX_HOME/skills` or `~/.codex/skills`
36
- - Claude Code gets a user subagent in `~/.claude/agents/agentbuilder.md`
36
+ - Codex and other coding agents (Cursor, Gemini CLI, GitHub Copilot, OpenCode,
37
+ and others) read it from `~/.agents/skills`
38
+ - Claude Code reads it from `~/.claude/skills`
37
39
 
38
- The implementation-agnostic specification guidance is a separate skill:
40
+ Without a terminal the command installs into `~/.agents/skills`. Use
41
+ `--agent agents` or `--agent claude` to skip the picker, and `--dir` for an
42
+ agent that reads skills from another directory, or for a project-level
43
+ install such as `.agents/skills`.
39
44
 
40
- ```bash
41
- npx skills add standardagents/skills@spec
42
- ```
43
-
44
- The `agentbuilder` skill defers to `spec` for what the specification requires,
45
- and it reads the published specification directly when `spec` is not installed.
45
+ There is one skill. The Standard Agent Specification is documentation, and the
46
+ `agentbuilder` skill tells the coding agent to read
47
+ `https://standardagentspec.org/llms.txt` and the pages it lists. When the skill
48
+ and the published specification disagree, the specification is correct.
46
49
 
47
50
  Package install:
48
51
 
@@ -69,13 +72,13 @@ Copy the editable markdown skill into a local skills directory:
69
72
  ```ts
70
73
  import { copySkill } from '@standardagents/skill'
71
74
 
72
- await copySkill('agentbuilder', '.codex/skills', { overwrite: true })
75
+ await copySkill('agentbuilder', '.agents/skills', { overwrite: true })
73
76
  ```
74
77
 
75
78
  That creates:
76
79
 
77
80
  ```text
78
- .codex/skills/
81
+ .agents/skills/
79
82
  agentbuilder/
80
83
  SKILL.md
81
84
  ```
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@standardagents/skill",
3
- "version": "0.45.0",
3
+ "version": "0.45.2",
4
4
  "private": false,
5
5
  "publishConfig": {
6
6
  "access": "public",
package/skills/agentbuilder/SKILL.md CHANGED
@@ -32,11 +32,15 @@ For deeper reference material that this skill links to, see:
32
32
 
33
33
  ## The specification comes first
34
34
 
35
- This skill covers how to build with AgentBuilder. The `spec` skill covers what the Standard Agent Specification requires, and it reads the published specification each time it runs.
35
+ This skill covers how to build with AgentBuilder. The published Standard Agent Specification defines what a Standard Agent is. Read it before you answer what the specification requires, decide whether an agent is portable, or write or review a definition that must conform. Do not answer from memory, and do not rely on a remembered version number.
36
36
 
37
- - Use the `spec` skill for questions about what the specification requires or whether an agent is portable.
38
- - If the `spec` skill is not available, read https://standardagentspec.org/llms.txt and the pages it lists. Tell the user once that `npx skills add standardagents/skills@spec` installs the skill.
39
- - If this skill and the published specification disagree, the specification is correct. Report the disagreement to the user.
37
+ 1. Read https://standardagentspec.org/llms.txt. Its `Latest version:` line names the latest version, and it lists a Markdown URL for every page of that version.
38
+ 2. Use the latest version unless the user or the project names another one. For a named older version, read `https://standardagentspec.org/api/navigation/<version>.json`. Each `href` in it becomes a Markdown URL when you put `https://standardagentspec.org` before it and `.md` after it.
39
+ 3. Read every page that governs the question, and follow links to the pages it depends on. Build URLs only from the index or the navigation file. Treat a response as not found unless its content type is `text/markdown`, or `text/plain` for `llms.txt`, because the site can answer an unknown path with an HTML page and status 200.
40
+ 4. Name the version and the pages you used in your answer. Separate what the specification requires from what it recommends and from your own inference. When the specification does not define something, say so.
41
+ 5. If you cannot reach the site, tell the user, and label anything you then say about the specification as unverified.
42
+
43
+ If this skill and the published specification disagree, the specification is correct. Report the disagreement to the user. AgentBuilder's types, source, and documentation, and this skill, describe AgentBuilder only.
40
44
 
41
45
  ## Keeping this skill up to date
42
46
 
@@ -47,8 +51,8 @@ This skill ships as `@standardagents/skill` on npm, and the version installed he
47
51
  1. If the stamp above still reads `__SKILL_VERSION__`, this is an unstamped development copy — skip this check.
48
52
  2. Run `npm view @standardagents/skill version`. If the command fails (offline, no npm, no shell access), skip silently. This check must never block, retry, or interrupt real work.
49
53
  3. If the published version is newer than the stamp, tell the user in one short line and offer to update. Updating overwrites this file — including any local edits — so get the user's OK before running:
50
- - Codex install (file lives under `.codex/skills/`): `npx @standardagents/cli@latest skill --force --agent codex`
51
- - Claude Code install (file lives under `.claude/agents/`): `npx @standardagents/cli@latest skill --force --agent claude`
54
+ - Claude Code install (file lives under `.claude/skills/`): `npx @standardagents/cli@latest skill --force --agent claude`
55
+ - Any other install (file lives under `.agents/skills/`, or under `.codex/skills/` from an earlier release): `npx @standardagents/cli@latest skill --force --agent agents`
52
56
  4. After updating, re-read the new file before continuing.
53
57
 
54
58
  Do this at most once per conversation, then move on to the task at hand.
@@ -837,6 +841,28 @@ Common failure modes:
837
841
 
838
842
  A prompt is what actually gets sent to the LLM at one step. Set on each prompt file in `agents/prompts/`. For full signatures, read the spec types from `node_modules/@standardagents/spec/dist/` (or browse `packages/spec/src/` on GitHub), and see `agents/prompts/AGENTS.md`.
839
843
 
844
+ Set `includePastTools` on every prompt that has tools to record the choice.
845
+ This includes callable tools, provider tools, and visible subagent lifecycle tools.
846
+ The specification defaults the flag to `false`.
847
+ With `false`, each request omits assistant tool calls and tool results from the running turn.
848
+ `includeChat: true` alone does not include tool history.
849
+
850
+ Choose `true` when a later step must read a tool result:
851
+
852
+ - The prompt answers from a tool result.
853
+ - A chained call uses an earlier result as input.
854
+ - The prompt answers from a blocking subagent result.
855
+
856
+ Choose `false` when the objective does not need earlier results in the request:
857
+
858
+ - The side ends its turn at the tool call.
859
+ - The tools only cause side effects.
860
+ - Results reach the model through another path, such as a hook summary or a subagent result message.
861
+ - Large or sensitive output must stay out of later requests.
862
+
863
+ A prompt that loops on tools with `false` may repeat calls until `maxSteps`.
864
+ Each prompt owns its flag.
865
+
840
866
  ```
841
867
  PromptDefinition
842
868
  name string unique snake_case identifier
@@ -844,7 +870,7 @@ PromptDefinition
844
870
  prompt string | PromptContent[] system prompt (string, or composable parts)
845
871
  model ModelName references agents/models/<name>
846
872
  includeChat boolean (default false) pass full chat history to this LLM step
847
- includePastTools boolean (default false) pass past tool call results
873
+ includePastTools boolean (default false) include tool calls and results in later requests
848
874
  parallelToolCalls boolean (default false) allow multiple tool calls per turn
849
875
  toolChoice 'auto' | 'none' | 'required' tool calling strategy (default 'auto')
850
876
  requiredSchema ZodSchema validate args when called as a tool