Commit Graph
30 Commits
Author SHA1 Message Date
ryan4yin | 二花 f32d67a5cc feat(agents): add review-comments-and-docs and two evaluation suites (#434)
Adds the review-comments-and-docs skill (1282-word body) and two evaluation suites: a 21-case
measured suite for the skill, and a harness that runs the two concurrency scenarios previously left
unrun in agents/evals/global-rules.md.
2026-10-12 00:35:06 +08:00
ryan4yin | 二花 497fabbf92 test(agents): tighten language rule eval (#430)
Assisted-by: DeepSeek Harness (gpt-6-luna)
2026-10-11 08:32:50 +08:00
Ryan Yin 648e375b88 test(agents): add git-delivery fixtures and an A/B run
Assisted-by: DeepSeek Harness (claude-opus-5-5, deepseek-flash, gpt-6.1-sol, gpt-6-luna)
2026-10-10 19:49:45 +08:00
Ryan Yin 7bba1abbc9 feat(agents): cap delivery text and shorten git-delivery
Assisted-by: DeepSeek Harness (claude-opus-5-5, deepseek-flash, qwen3.8-flash-next iq3, gpt-6.1-sol, gpt-6-luna)
2026-10-10 19:49:44 +08:00
Ryan Yin a100790ff2 feat(agents): require self-explaining artifacts and readable brevity
Assisted-by: DeepSeek Harness (qwen3.8-flash-next iq3, gpt-6.1-sol, gpt-6-luna)
2026-10-10 19:49:44 +08:00
Ryan Yin 0e70582642 docs(agents): convert prose tables to grouped lists
Assisted-by: DeepSeek Harness (claude-opus-5-5, qwen3.8-flash-next iq3)
2026-10-10 19:49:44 +08:00
Ryan Yin d808dd914d docs(agents): correct rule boundaries and eval scenarios
Assisted-by: DeepSeek Harness (claude-opus-5-5, deepseek-flash, qwen3.8-flash-next iq3)
2026-10-10 19:49:44 +08:00
ryan4yin | 二花 e2548cd2aa docs(agents): close rule gaps found by evals and record the method (#428)
* docs(agents): state the boundaries the rules only implied
* docs(agents): grow the scenario tables and record the method
* docs(agents): record the evaluation rounds and their size cost
* docs(agents): require disclosure of AI-assisted contributions
* docs(agents): correct safety boundaries and eval records

Assisted-by: DeepSeek Harness (qwen3.8-flash-next iq3, gpt-6-luna & gpt-6.1-sol)
2026-10-10 15:59:57 +08:00
ryan4yin | 二花 9d69832ff7 refactor(agents): pin global skills and trim always-loaded context (#427)
* feat(agents): pin global skills as flake inputs
* refactor(agents): trim always-loaded agent context
2026-10-10 12:16:56 +08:00
ryan4yin | 二花 0d7c4d7cc1 feat(agents): extract global Git delivery skill #426 2026-10-10 11:18:39 +08:00
Ryan Yin 3b63028a05 fix: repair skill frontmatter and cap commit message length 2026-10-10 09:02:08 +08:00
Ryan Yin 2d07dc8da5 docs(agents): close rule gaps behind repeated corrections
Clause-level extensions only, no new sections. Publishing gains modals in both directions: the old sentence read as forbidding pushes to the user's own private repositories while leaving the disclosure direction a preference. The diagnosis scenario moves to Smoke because a cross-cutting rule has no area for the Extended trigger to select, and the guide separates cheap checks from behavioral runs so a modal-only edit does not cost a scenario suite.
2026-10-10 08:42:38 +08:00
Ryan Yin dd46fb3fb2 docs(agents): clarify credential boundaries and rule maintenance 2026-10-08 23:45:47 +08:00
Ryan Yin 97237f352d docs(agents): use the Nix-managed GitHub SSH config
Restore the rule dropped in 9822dafa: keep GitHub Git remotes on SSH, make sure the Nix-managed ~/.ssh/config is used, and rerun outside the sandbox when it is rejected.
2026-10-04 14:32:32 +08:00
Ryan Yin 9885283edf docs(agents): clarify local language selection and prefer Bun 2026-10-01 10:23:35 +08:00
Ryan Yin 7f6759219b docs(agents): align evals with external instruction boundaries 2026-09-30 21:17:19 +08:00
Ryan Yin 91cc9c0cf4 docs(agents): fix authorization and skill trust wording
Allow clearly-implied task authorization, trust skills listed in the runtime's configured catalog, and restore the ban on following external-material instructions. Sync the affected evaluation scenarios.
2026-09-30 21:09:34 +08:00
ryan4yin | 二花 111929023d docs(agents): clarify tool selection and authorization boundaries (#331) 2026-09-30 20:51:42 +08:00
Ryan Yin bae98ed1c8 docs(agents): allow TypeScript for complex shell commands 2026-09-30 18:38:08 +08:00
ryan4yin | 二花 f326dcb139 docs(agents): Simplifies global rules so agents can understand and follow it easily (#323) 2026-09-26 09:51:42 +08:00
Ryan Yin cc1655a059 docs(agents): normalize gating terms and drop duplicate clauses
Use one wording per gating family: exact target and scope, recovery path or safety guard, and explicit authorization. Remove the home-directory instance from workspace access and the repeated approval gate from the breaking-change bullet. Sync the high-impact eval scenario wording.
2026-09-19 08:50:17 +08:00
Ryan Yin 02346df157 docs(agents): gate irreversible operations and generalize preview validity
State the destructive-and-high-impact section as a principle: irreversible operations need explicit authorization, destructive or force operations form a separate categorical gate, and unpublished history rewrites are exempt at section level. Generalize infrastructure preview invalidation to any input change, and add an irreversible-action eval scenario.
2026-09-19 08:26:41 +08:00
Ryan Yin f260d17d3b docs(agents): refine user-edit and test-double rules
Generalize the revert rule to protect any content the user changed or removed, and require confirmation before touching it. Replace the mock ban with a scope rule: checks must not be faked or weakened, and test doubles may replace only what a check does not verify. Sync the matching eval scenario.
2026-09-19 07:52:16 +08:00
Ryan Yin 6d2455ad4e docs(agents): drop redundant handling and precedence rules
- remove the Request handling and Scope and precedence sections
- keep the non-weakening guarantee under Safety and authorization
- remove the now-stale eval scenarios
2026-09-14 20:48:56 +08:00
Ryan Yin c86edde9a2 docs(agents): streamline global rules
- merge verification rules and split infrastructure guidance
- shorten Tools, Shell/scripts, and Communication
- apply script validation to any script file, including temporary ones
- sync evals
2026-09-14 20:39:49 +08:00
ryan4yin | 二花 85af66801f docs(agents): add SRE change guardrails and refine global rules (#269)
* docs(agents): bind authorization to the change boundary

* docs(agents): require target identity confirmation

* docs(agents): classify operations by impact, not command form

* docs(agents): require reviewed previews for high-risk IaC

* docs(agents): verify production changes beyond exit codes

* docs(agents): sync new-script eval with current rules

* docs(agents): split global rules evals into smoke and extended

* docs(agents): refine change guardrails wording

- scope the guardrails to any environment, not only production
- preview high-risk changes with plan, diff, or dry-run
- trim redundant examples and simplify target identity confirmation
- confirm unclear targets with the user instead of stopping
2026-09-14 20:28:21 +08:00
Ryan Yin 9fa975887d docs(agents): clarify authorization reuse and task baselines 2026-09-05 14:17:31 +08:00
Ryan Yin dc261e2934 docs(agents): focus global rules and script validation 2026-09-01 18:33:26 +08:00
Ryan Yin 9822dafa89 docs(agents): refine global agent rules 2026-08-31 18:35:17 +08:00
Ryan Yin bed0359a0d docs(agents): standardize global rule semantics 2026-08-31 16:37:07 +08:00