liteagents 2.21.0 → 2.21.1
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.
- package/CHANGELOG.md +10 -0
- package/package.json +1 -1
- package/packages/ampcode/commands/remember/AGENT_RULES.md +3 -3
- package/packages/claude/commands/remember/AGENT_RULES.md +3 -3
- package/packages/droid/commands/remember/AGENT_RULES.md +3 -3
- package/packages/opencode/command/remember/AGENT_RULES.md +3 -3
package/CHANGELOG.md
CHANGED
|
@@ -9,6 +9,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
9
9
|
|
|
10
10
|
## [Unreleased]
|
|
11
11
|
|
|
12
|
+
## [2.21.1] - 2026-08-30
|
|
13
|
+
|
|
14
|
+
### Changed
|
|
15
|
+
- **`AGENT_RULES.md` template points at `/branch-review`, in all four kits.** Three sites
|
|
16
|
+
still described the pre-2.21.0 topology: Operating Flow §2 and the Security invariants both
|
|
17
|
+
told the agent to run `/security` separately and lean on `/ship` as the security gate, and
|
|
18
|
+
the never-commit-to-`main` safeguard named `/code-review`. They now say: propose
|
|
19
|
+
`/branch-review` (general review plus a full `/security` audit, reports and never fixes),
|
|
20
|
+
then `/release` (which runs `/ship` as the mechanical pre-deploy gate).
|
|
21
|
+
|
|
12
22
|
## [2.21.0] - 2026-08-30
|
|
13
23
|
|
|
14
24
|
### Changed
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "liteagents",
|
|
3
|
-
"version": "2.21.
|
|
3
|
+
"version": "2.21.1",
|
|
4
4
|
"description": "AI development toolkit with 11 specialized agents and 18 commands including live-canvas UI design with click-to-annotate feedback. Simple one-question installer for Claude, Opencode, Ampcode, and Droid.",
|
|
5
5
|
"main": "index.js",
|
|
6
6
|
"bin": {
|
|
@@ -27,7 +27,7 @@ Every task runs through three layers. Do not skip ahead to code.
|
|
|
27
27
|
- **Open questions** — unknowns that don't block; never silently assumed
|
|
28
28
|
|
|
29
29
|
Every POC result updates the PRD; one that flips the go/no-go or a module's assumption is a spec change, not a footnote.
|
|
30
|
-
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)).
|
|
30
|
+
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)). When the work is done, propose `/branch-review` — a general review plus a full `/security` audit, which reports findings and never fixes them — and then `/release`, which runs `/ship` as the mechanical pre-deploy gate. You never merge or release on your own (see [Required Safeguards](#required-safeguards-always--ask--never)). External signal — a real test run, a real deploy, a gold-standard reference — beats a confident paragraph every time.
|
|
31
31
|
3. **Environment — the standing context.** This file primes every session. Critical-path protections (secrets, auth, schema, CI) are stated as **Always / Ask / Never** below and bind you as written. Where your tool offers a permission allow/ask/deny list, mirror them there so they are enforced and not merely requested.
|
|
32
32
|
|
|
33
33
|
**Execution order — work the way a program runs, in this order, nothing skipped:**
|
|
@@ -61,7 +61,7 @@ Not courtesies. These bind you as written, whether or not your tool enforces the
|
|
|
61
61
|
- **Always** identify affected files before making changes, and explain what will change and why
|
|
62
62
|
- **Ask first** — stop and get explicit sign-off — before modifying authentication systems, database schema or migrations, CI workflows, or `.amp/settings.json`
|
|
63
63
|
- **Never** write secrets into the tree (`.env`/`*.env`, keys, credentials). They load from the environment at runtime; only a value-less `.env.example` is committed
|
|
64
|
-
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/
|
|
64
|
+
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/branch-review` followed by `/release`; merging and releasing are my call, made by name — "approve", "good", or "go" on a draft is not that call
|
|
65
65
|
|
|
66
66
|
---
|
|
67
67
|
|
|
@@ -229,7 +229,7 @@ Also hold the line on: input validation at every trust boundary (untrusted uploa
|
|
|
229
229
|
|
|
230
230
|
**Verify at two moments, not one.**
|
|
231
231
|
- **While building** — this list shapes the code as it's written.
|
|
232
|
-
- **Before deploy/merge** — run **`/security`**
|
|
232
|
+
- **Before deploy/merge** — run **`/branch-review`**, whose second stage runs **`/security`** in full; `/release` then runs **`/ship`** as the mechanical pre-deploy gate. A Critical/High finding blocks the ship; lower-severity findings get logged and triaged, not silently shipped. Proactively remind the user to run them whenever a change touches auth, data access, endpoints, secrets, or untrusted input.
|
|
233
233
|
|
|
234
234
|
---
|
|
235
235
|
|
|
@@ -27,7 +27,7 @@ Every task runs through three layers. Do not skip ahead to code.
|
|
|
27
27
|
- **Open questions** — unknowns that don't block; never silently assumed
|
|
28
28
|
|
|
29
29
|
Every POC result updates the PRD; one that flips the go/no-go or a module's assumption is a spec change, not a footnote.
|
|
30
|
-
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)).
|
|
30
|
+
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)). When the work is done, propose `/branch-review` — a general review plus a full `/security` audit, which reports findings and never fixes them — and then `/release`, which runs `/ship` as the mechanical pre-deploy gate. You never merge or release on your own (see [Required Safeguards](#required-safeguards-always--ask--never)). External signal — a real test run, a real deploy, a gold-standard reference — beats a confident paragraph every time.
|
|
31
31
|
3. **Environment — the standing context.** This file primes every session. Critical-path protections (secrets, auth, schema, CI) are stated as **Always / Ask / Never** below and bind you as written. Where your tool offers a permission allow/ask/deny list, mirror them there so they are enforced and not merely requested.
|
|
32
32
|
|
|
33
33
|
**Execution order — work the way a program runs, in this order, nothing skipped:**
|
|
@@ -61,7 +61,7 @@ Not courtesies. These bind you as written, whether or not your tool enforces the
|
|
|
61
61
|
- **Always** identify affected files before making changes, and explain what will change and why
|
|
62
62
|
- **Ask first** — stop and get explicit sign-off — before modifying authentication systems, database schema or migrations, CI workflows, or `.claude/settings.json`
|
|
63
63
|
- **Never** write secrets into the tree (`.env`/`*.env`, keys, credentials). They load from the environment at runtime; only a value-less `.env.example` is committed
|
|
64
|
-
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/
|
|
64
|
+
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/branch-review` followed by `/release`; merging and releasing are my call, made by name — "approve", "good", or "go" on a draft is not that call
|
|
65
65
|
|
|
66
66
|
---
|
|
67
67
|
|
|
@@ -229,7 +229,7 @@ Also hold the line on: input validation at every trust boundary (untrusted uploa
|
|
|
229
229
|
|
|
230
230
|
**Verify at two moments, not one.**
|
|
231
231
|
- **While building** — this list shapes the code as it's written.
|
|
232
|
-
- **Before deploy/merge** — run **`/security`**
|
|
232
|
+
- **Before deploy/merge** — run **`/branch-review`**, whose second stage runs **`/security`** in full; `/release` then runs **`/ship`** as the mechanical pre-deploy gate. A Critical/High finding blocks the ship; lower-severity findings get logged and triaged, not silently shipped. Proactively remind the user to run them whenever a change touches auth, data access, endpoints, secrets, or untrusted input.
|
|
233
233
|
|
|
234
234
|
---
|
|
235
235
|
|
|
@@ -27,7 +27,7 @@ Every task runs through three layers. Do not skip ahead to code.
|
|
|
27
27
|
- **Open questions** — unknowns that don't block; never silently assumed
|
|
28
28
|
|
|
29
29
|
Every POC result updates the PRD; one that flips the go/no-go or a module's assumption is a spec change, not a footnote.
|
|
30
|
-
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)).
|
|
30
|
+
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)). When the work is done, propose `/branch-review` — a general review plus a full `/security` audit, which reports findings and never fixes them — and then `/release`, which runs `/ship` as the mechanical pre-deploy gate. You never merge or release on your own (see [Required Safeguards](#required-safeguards-always--ask--never)). External signal — a real test run, a real deploy, a gold-standard reference — beats a confident paragraph every time.
|
|
31
31
|
3. **Environment — the standing context.** This file primes every session. Critical-path protections (secrets, auth, schema, CI) are stated as **Always / Ask / Never** below and bind you as written. Where your tool offers a permission allow/ask/deny list, mirror them there so they are enforced and not merely requested.
|
|
32
32
|
|
|
33
33
|
**Execution order — work the way a program runs, in this order, nothing skipped:**
|
|
@@ -61,7 +61,7 @@ Not courtesies. These bind you as written, whether or not your tool enforces the
|
|
|
61
61
|
- **Always** identify affected files before making changes, and explain what will change and why
|
|
62
62
|
- **Ask first** — stop and get explicit sign-off — before modifying authentication systems, database schema or migrations, CI workflows, or `.factory/settings.json`
|
|
63
63
|
- **Never** write secrets into the tree (`.env`/`*.env`, keys, credentials). They load from the environment at runtime; only a value-less `.env.example` is committed
|
|
64
|
-
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/
|
|
64
|
+
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/branch-review` followed by `/release`; merging and releasing are my call, made by name — "approve", "good", or "go" on a draft is not that call
|
|
65
65
|
|
|
66
66
|
---
|
|
67
67
|
|
|
@@ -229,7 +229,7 @@ Also hold the line on: input validation at every trust boundary (untrusted uploa
|
|
|
229
229
|
|
|
230
230
|
**Verify at two moments, not one.**
|
|
231
231
|
- **While building** — this list shapes the code as it's written.
|
|
232
|
-
- **Before deploy/merge** — run **`/security`**
|
|
232
|
+
- **Before deploy/merge** — run **`/branch-review`**, whose second stage runs **`/security`** in full; `/release` then runs **`/ship`** as the mechanical pre-deploy gate. A Critical/High finding blocks the ship; lower-severity findings get logged and triaged, not silently shipped. Proactively remind the user to run them whenever a change touches auth, data access, endpoints, secrets, or untrusted input.
|
|
233
233
|
|
|
234
234
|
---
|
|
235
235
|
|
|
@@ -27,7 +27,7 @@ Every task runs through three layers. Do not skip ahead to code.
|
|
|
27
27
|
- **Open questions** — unknowns that don't block; never silently assumed
|
|
28
28
|
|
|
29
29
|
Every POC result updates the PRD; one that flips the go/no-go or a module's assumption is a spec change, not a footnote.
|
|
30
|
-
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)).
|
|
30
|
+
2. **Verify — define "good" up front, then prove it.** Write down what success looks like *before* changing code. Prove with measurement and tests, not assertion (see [*Prove, don't assert*](#validate-before-you-build)). When the work is done, propose `/branch-review` — a general review plus a full `/security` audit, which reports findings and never fixes them — and then `/release`, which runs `/ship` as the mechanical pre-deploy gate. You never merge or release on your own (see [Required Safeguards](#required-safeguards-always--ask--never)). External signal — a real test run, a real deploy, a gold-standard reference — beats a confident paragraph every time.
|
|
31
31
|
3. **Environment — the standing context.** This file primes every session. Critical-path protections (secrets, auth, schema, CI) are stated as **Always / Ask / Never** below and bind you as written. Where your tool offers a permission allow/ask/deny list, mirror them there so they are enforced and not merely requested.
|
|
32
32
|
|
|
33
33
|
**Execution order — work the way a program runs, in this order, nothing skipped:**
|
|
@@ -61,7 +61,7 @@ Not courtesies. These bind you as written, whether or not your tool enforces the
|
|
|
61
61
|
- **Always** identify affected files before making changes, and explain what will change and why
|
|
62
62
|
- **Ask first** — stop and get explicit sign-off — before modifying authentication systems, database schema or migrations, CI workflows, or `.opencode/settings.json`
|
|
63
63
|
- **Never** write secrets into the tree (`.env`/`*.env`, keys, credentials). They load from the environment at runtime; only a value-less `.env.example` is committed
|
|
64
|
-
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/
|
|
64
|
+
- **Never** commit to `main`. Commit to a new branch (name doesn't matter), then propose `/branch-review` followed by `/release`; merging and releasing are my call, made by name — "approve", "good", or "go" on a draft is not that call
|
|
65
65
|
|
|
66
66
|
---
|
|
67
67
|
|
|
@@ -229,7 +229,7 @@ Also hold the line on: input validation at every trust boundary (untrusted uploa
|
|
|
229
229
|
|
|
230
230
|
**Verify at two moments, not one.**
|
|
231
231
|
- **While building** — this list shapes the code as it's written.
|
|
232
|
-
- **Before deploy/merge** — run **`/security`**
|
|
232
|
+
- **Before deploy/merge** — run **`/branch-review`**, whose second stage runs **`/security`** in full; `/release` then runs **`/ship`** as the mechanical pre-deploy gate. A Critical/High finding blocks the ship; lower-severity findings get logged and triaged, not silently shipped. Proactively remind the user to run them whenever a change touches auth, data access, endpoints, secrets, or untrusted input.
|
|
233
233
|
|
|
234
234
|
---
|
|
235
235
|
|