trace-to-skill 0.1.88 → 0.1.89

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 (8) hide show
  1. package/README.md +34 -34
  2. package/dist/src/init.js +3 -3
  3. package/docs/CODEX_ISSUE_RADAR.md +112 -0
  4. package/docs/DISCOVERY.md +4 -1
  5. package/docs/OPENAI_OSS_BRIEF.md +2 -2
  6. package/docs/USE_CASES.md +2 -2
  7. package/llms.txt +5 -3
  8. package/package.json +2 -1
package/README.md CHANGED
@@ -8,39 +8,38 @@
8
8
  [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
9
9
  [![Node](https://img.shields.io/badge/node-%3E%3D20-339933.svg)](package.json)
10
10
 
11
- Turn failed AI coding-agent runs into reusable `AGENTS.md` rules, `SKILL.md` files, and eval evidence.
11
+ Codex Issue Radar and maintainer-readiness tooling for open-source projects using AI coding agents.
12
+
13
+ `trace-to-skill` turns live GitHub issue demand, failed Codex/agent runs, and repository readiness checks into evidence-backed reports, `AGENTS.md` rules, `SKILL.md` workflows, and CI gates.
14
+
15
+ ## Start Here
16
+
17
+ Run a live Codex issue radar:
18
+
19
+ ```bash
20
+ npx trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
21
+ ```
22
+
23
+ Install a weekly radar in any repository:
12
24
 
13
25
  ```bash
14
- npx trace-to-skill demo
15
- npx trace-to-skill doctor .
16
- npx trace-to-skill lint-agents .
17
- npx trace-to-skill analyze ./runs
18
- npx trace-to-skill codex-report ./runs
19
- npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
20
- npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
21
- npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
22
- npx trace-to-skill init --comment --sarif
23
26
  npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --issue-map-limit 100
24
- npx trace-to-skill suggest ./runs --target agents-md
25
- npx trace-to-skill eval ./runs --threshold 80
26
- npx trace-to-skill benchmark
27
+ ```
28
+
29
+ Check whether a repo is Codex-ready:
30
+
31
+ ```bash
27
32
  npx trace-to-skill scorecard .
28
- npx trace-to-skill oss-brief .
29
- npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
30
- npx trace-to-skill scorecard-comment . --dry-run
31
- npx trace-to-skill guard-github-event "$GITHUB_EVENT_PATH"
32
- npx trace-to-skill guard-patch ./change.patch --root .
33
- npx trace-to-skill session-audit ~/.codex --format json
34
- npx trace-to-skill sensitive-audit . --format json
35
- npx trace-to-skill sensitive-audit . --format ignore --ignore-target codexignore --output .codexignore.generated
36
- npx trace-to-skill lsp-audit . --format json
37
- npx trace-to-skill config-audit ~/.codex --format json
38
- npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format json
39
- npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
40
- npx trace-to-skill comment ./runs --dry-run
41
- npx trace-to-skill compare --before ./runs/before --after ./runs/after
42
33
  ```
43
34
 
35
+ Package a failed run into a better OpenAI/Codex issue:
36
+
37
+ ```bash
38
+ npx trace-to-skill codex-report ./runs --output openai-codex-issue.md
39
+ ```
40
+
41
+ See the live generated example: [docs/CODEX_ISSUE_RADAR.md](docs/CODEX_ISSUE_RADAR.md). For the full command catalog, use [docs/USE_CASES.md](docs/USE_CASES.md).
42
+
44
43
  AI coding agents are getting good enough to change real repositories, but they still repeat the same workflow mistakes: claiming success without tests, ignoring repo instructions, over-editing, inventing files, leaking secrets into traces, or enabling risky MCP tools.
45
44
 
46
45
  `trace-to-skill` closes that loop:
@@ -107,7 +106,7 @@ Use it when you need to:
107
106
  - **File better OpenAI/Codex issues:** run `trace-to-skill codex-report ./runs` to turn a failed trace into a redaction-aware, copy-paste-ready issue body with evidence and diagnostics.
108
107
  - **Package quota bugs cleanly:** run `trace-to-skill analyze ./runs` on Codex traces where `/status` or the usage page shows remaining quota but the client returns `You've hit your usage limit`.
109
108
 
110
- For copy-paste workflows, see [docs/USE_CASES.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/USE_CASES.md). For Codex issue clusters, see [docs/CODEX_ISSUE_MAP.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_MAP.md) and [docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md). For crawler-friendly metadata, see [docs/DISCOVERY.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/DISCOVERY.md) and [llms.txt](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/llms.txt).
109
+ For copy-paste workflows, see [docs/USE_CASES.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/USE_CASES.md). For live Codex issue demand, see [docs/CODEX_ISSUE_RADAR.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_RADAR.md), [docs/CODEX_ISSUE_MAP.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_MAP.md), and [docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md). For crawler-friendly metadata, see [docs/DISCOVERY.md](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/DISCOVERY.md) and [llms.txt](https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/llms.txt).
111
110
 
112
111
  ## Why This Exists
113
112
 
@@ -415,8 +414,9 @@ See this repository's current brief in [docs/OPENAI_OSS_BRIEF.md](docs/OPENAI_OS
415
414
  Mine public GitHub issue demand into a maintainer pain map:
416
415
 
417
416
  ```bash
418
- trace-to-skill issue-map --repo openai/codex --limit 100 --output codex-issue-map.md
417
+ trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
419
418
  trace-to-skill issue-map --repo openai/codex --format json
419
+ trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --issue-map-limit 100
420
420
  gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
421
421
  trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
422
422
  trace-to-skill issue-map codex-issues.json --format json
@@ -424,7 +424,7 @@ trace-to-skill issue-map codex-issues.json --format json
424
424
 
425
425
  `issue-map` can fetch a public GitHub repository directly through the GitHub REST API, or read JSON exported by `gh issue list` / `gh search issues`. It analyzes each issue with the same deterministic failure detectors and ranks clusters by issue count, comment count, reactions, and severity. Use it to decide what people are actively asking for on GitHub before adding the next fixture, Codex report template, diagnostic bundle, or OpenAI-ready support artifact.
426
426
 
427
- To map a Codex problem to the right failure class and report command, see [docs/CODEX_ISSUE_MAP.md](docs/CODEX_ISSUE_MAP.md).
427
+ For a live generated radar, see [docs/CODEX_ISSUE_RADAR.md](docs/CODEX_ISSUE_RADAR.md). To map a Codex problem to the right failure class and report command, see [docs/CODEX_ISSUE_MAP.md](docs/CODEX_ISSUE_MAP.md).
428
428
 
429
429
  Create a local pre-agent workspace checkpoint:
430
430
 
@@ -537,7 +537,7 @@ jobs:
537
537
  issues: write
538
538
  steps:
539
539
  - uses: actions/checkout@v5
540
- - uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
540
+ - uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
541
541
  with:
542
542
  mode: all
543
543
  doctor-threshold: "85"
@@ -586,7 +586,7 @@ Composite action usage:
586
586
 
587
587
  ```yaml
588
588
  - id: trace-to-skill
589
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
589
+ uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
590
590
  with:
591
591
  mode: all
592
592
  doctor-threshold: "85"
@@ -604,7 +604,7 @@ Issue-map action usage for direct GitHub issue demand mining:
604
604
 
605
605
  ```yaml
606
606
  - id: codex-issue-map
607
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
607
+ uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
608
608
  with:
609
609
  mode: issue-map
610
610
  issue-map-repo: openai/codex
@@ -648,7 +648,7 @@ Action outputs:
648
648
 
649
649
  By default, generated reports are also appended to the GitHub Actions Job Summary. Set `job-summary: "false"` to disable that UI output.
650
650
 
651
- Tagged Action releases build and run the CLI from `$GITHUB_ACTION_PATH`, so a workflow pinned to a release tag such as `@v0.1.88` executes that release's checked-out source instead of pulling the default branch at runtime.
651
+ Tagged Action releases build and run the CLI from `$GITHUB_ACTION_PATH`, so a workflow pinned to a release tag such as `@v0.1.89` executes that release's checked-out source instead of pulling the default branch at runtime.
652
652
 
653
653
  ## Codex Skill
654
654
 
package/dist/src/init.js CHANGED
@@ -99,7 +99,7 @@ function renderCodexReadinessWorkflow(doctorThreshold, comment) {
99
99
  " steps:",
100
100
  " - uses: actions/checkout@v5",
101
101
  " - id: trace-to-skill",
102
- " uses: grnbtqdbyx-create/trace-to-skill@v0.1.88",
102
+ " uses: grnbtqdbyx-create/trace-to-skill@v0.1.89",
103
103
  " with:",
104
104
  " mode: all",
105
105
  ` doctor-threshold: "${doctorThreshold}"`,
@@ -126,7 +126,7 @@ function renderAgentLearningWorkflow(traces, threshold, comment, sarif) {
126
126
  const steps = [
127
127
  " - uses: actions/checkout@v5",
128
128
  " - id: trace-to-skill",
129
- " uses: grnbtqdbyx-create/trace-to-skill@v0.1.88",
129
+ " uses: grnbtqdbyx-create/trace-to-skill@v0.1.89",
130
130
  " with:",
131
131
  " mode: traces",
132
132
  ` traces: ${traces}`,
@@ -173,7 +173,7 @@ function renderIssueRadarWorkflow(repo, state, limit) {
173
173
  " steps:",
174
174
  " - uses: actions/checkout@v5",
175
175
  " - id: issue-map",
176
- " uses: grnbtqdbyx-create/trace-to-skill@v0.1.88",
176
+ " uses: grnbtqdbyx-create/trace-to-skill@v0.1.89",
177
177
  " with:",
178
178
  " mode: issue-map",
179
179
  ` issue-map-repo: ${repo}`,
package/docs/CODEX_ISSUE_RADAR.md ADDED
@@ -0,0 +1,112 @@
1
+ # Codex Issue Radar Demo
2
+
3
+ Generated: 2026-06-01T01:58:02.397Z
4
+
5
+ Issues analyzed: **46**
6
+ Matched issues: **14**
7
+ Unmatched issues: **32**
8
+
9
+ This public demo maps live `openai/codex` GitHub issues onto deterministic `trace-to-skill` failure classes. It is designed as a maintainer-facing signal: which public pain points have enough comments/reactions to become the next support artifact, fixture, `AGENTS.md` rule, or Codex workflow improvement.
10
+
11
+ Fetch a repository directly with `--repo`, or export issues with `gh issue list` / `gh search issues` and pass the JSON file.
12
+
13
+ ```bash
14
+ trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
15
+ gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
16
+ trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
17
+ ```
18
+
19
+ Install a weekly/manual radar workflow in a repository:
20
+
21
+ ```bash
22
+ trace-to-skill init --issue-map-repo owner/name --issue-map-state all --issue-map-limit 100
23
+ ```
24
+
25
+ ## Top Clusters
26
+
27
+ | Priority | Kind | Severity | Issues | Comments | Reactions | Example |
28
+ | ---: | --- | --- | ---: | ---: | ---: | --- |
29
+ | 2221 | `weak_evidence` | medium | 46 | 4754 | 7792 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
30
+ | 1929 | `codex_token_burn` | high | 3 | 826 | 533 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
31
+ | 884 | `sensitive_file_access` | high | 1 | 75 | 396 | [#2847 A way to exclude sensitive files](https://github.com/openai/codex/issues/2847) | |
32
+ | 442 | `codex_tool_call_integrity` | high | 1 | 61 | 182 | [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) | |
33
+ | 376 | `codex_remote_compact` | high | 2 | 147 | 101 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
34
+ | 376 | `context_compaction` | high | 2 | 147 | 101 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
35
+ | 351 | `codex_terminal_output_integrity` | high | 1 | 66 | 134 | [#2558 Codex client output truncated when scrolling in Zellij](https://github.com/openai/codex/issues/2558) | |
36
+ | 261 | `premature_completion` | high | 1 | 60 | 92 | [#2448 Codex CLI: Plus users hitting usage limits extremely quickly compared to competitors](https://github.com/openai/codex/issues/2448) | |
37
+ | 247 | `codex_connectivity` | high | 2 | 192 | 14 | [#12764 The codex cli giving: 401 unauthorized](https://github.com/openai/codex/issues/12764) | |
38
+ | 181 | `codex_latest_turn_drift` | high | 1 | 58 | 53 | [#8648 Codex replies to earlier messages instead of latest one in conversations](https://github.com/openai/codex/issues/8648) | |
39
+ | 168 | `codex_resource_leak` | high | 1 | 97 | 27 | [#10432 High GPU usage (70–90%) on macOS with Codex app](https://github.com/openai/codex/issues/10432) | |
40
+ | 128 | `codex_mcp_discovery_mismatch` | high | 1 | 55 | 28 | [#6465 MCP servers not detected in Codex VS Code extension (but working in Codex CLI)](https://github.com/openai/codex/issues/6465) | |
41
+
42
+ ## Suggested Next Actions
43
+
44
+ ### weak_evidence
45
+
46
+ Priority score: 2221. 46 issue(s), 4754 comment(s).
47
+
48
+ Example issues:
49
+ - [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
50
+ - [#13568 Usage dropping too quickly](https://github.com/openai/codex/issues/13568) (325 comments; labels: bug, rate-limits)
51
+ - [#10410 Codex Desktop App: macOS Intel (x86_64) support](https://github.com/openai/codex/issues/10410) (190 comments; labels: enhancement, app)
52
+
53
+ Evidence rule prompts:
54
+ - Final responses must include the exact validation evidence used to prove the change, not only a summary of intent.
55
+
56
+ ### codex_token_burn
57
+
58
+ Priority score: 1929. 3 issue(s), 826 comment(s).
59
+
60
+ Example issues:
61
+ - [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
62
+ - [#19464 Support 1M token context for GPT-5.5 in Codex](https://github.com/openai/codex/issues/19464) (132 comments; labels: enhancement, context)
63
+ - [#13186 Possible Codex usage metering anomaly on Plus (very small tasks consuming large 5h + weekly quota)](https://github.com/openai/codex/issues/13186) (101 comments; labels: bug, rate-limits, CLI)
64
+
65
+ Evidence rule prompts:
66
+ - When reporting Codex token burn, capture plan/workspace, client and version, model and reasoning/speed settings, fast-mode/large-context/subagent/review flags, recent /status and usage-dashboard deltas, local token totals including cached input/output/reasoning if available, background process ids and write_stdin poll cadence, compaction attempts and failures, retry/tool-loop counts, whether the app was idle, and a minimal reproduction with before/after usage percentages.
67
+
68
+ ### sensitive_file_access
69
+
70
+ Priority score: 884. 1 issue(s), 75 comment(s).
71
+
72
+ Example issues:
73
+ - [#2847 A way to exclude sensitive files](https://github.com/openai/codex/issues/2847) (75 comments; labels: enhancement, sandbox)
74
+
75
+ Evidence rule prompts:
76
+ - Before running an agent, exclude sensitive files such as .env, private keys, package auth files, cloud credentials, local databases, and production secret manifests; share only minimal redacted excerpts when maintainer-approved.
77
+
78
+ ### codex_tool_call_integrity
79
+
80
+ Priority score: 442. 1 issue(s), 61 comment(s).
81
+
82
+ Example issues:
83
+ - [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) (61 comments; labels: enhancement, extension)
84
+
85
+ Evidence rule prompts:
86
+ - When reporting Codex tool-call integrity failures, capture the exact tool input and output, app/CLI/extension version, OS/IDE, workspace git state, affected file path and whether it already existed or was a symlink, diff before/after, tool_call_id sequence, durable thread state for subagents, rollback/revert attempts, and whether a clean repo reproduction fails the same way.
87
+
88
+ ### codex_remote_compact
89
+
90
+ Priority score: 376. 2 issue(s), 147 comment(s).
91
+
92
+ Example issues:
93
+ - [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
94
+ - [#9544 Error running remote compact task: stream disconnected before completion](https://github.com/openai/codex/issues/9544) (57 comments; labels: bug, context)
95
+
96
+ Evidence rule prompts:
97
+ - When reporting Codex remote compact failures, capture app/CLI/extension version, OS, model and reasoning/speed mode, provider config without secrets, exact /compact or auto-compact error, `responses/compact` endpoint shape, timeout values such as tcp_user_timeout or stream_idle_timeout_ms, context/token level before compaction, whether lowering reasoning/speed changes behavior, whether local fallback or a new session recovers, and related thread/feedback ids.
98
+
99
+ ## Unmatched Issues
100
+
101
+ - [#13568 Usage dropping too quickly](https://github.com/openai/codex/issues/13568) (325 comments; labels: bug, rate-limits)
102
+ - [#10410 Codex Desktop App: macOS Intel (x86_64) support](https://github.com/openai/codex/issues/10410) (190 comments; labels: enhancement, app)
103
+ - [#20161 Phone number verification doesn't work](https://github.com/openai/codex/issues/20161) (176 comments; labels: bug, auth)
104
+ - [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) (176 comments; labels: enhancement, app)
105
+ - [#1243 "Sign in With ChatGPT" functionality needs to be robust against all account types](https://github.com/openai/codex/issues/1243) (169 comments; labels: none)
106
+ - [#11189 GPT-5.3-Codex being routed to GPT-5.2](https://github.com/openai/codex/issues/11189) (169 comments; labels: bug, CLI)
107
+ - [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) (160 comments; labels: bug, context, app)
108
+ - [#14048 All models — Codex CLI hangs indefinitely on all prompts, no response generated](https://github.com/openai/codex/issues/14048) (131 comments; labels: bug, agent)
109
+ - [#2604 Subagent Support](https://github.com/openai/codex/issues/2604) (103 comments; labels: enhancement, subagent)
110
+ - [#2841 “Error starting conversation” in new Codex VS Code extension when initializing a chat](https://github.com/openai/codex/issues/2841) (90 comments; labels: bug, windows-os, extension)
111
+ - [#12564 Allow renaming task/thread titles to improve history navigation](https://github.com/openai/codex/issues/12564) (77 comments; labels: enhancement, extension)
112
+ - [#2860 Unusable on Windows due to permission ask for every shell command](https://github.com/openai/codex/issues/2860) (77 comments; labels: bug, windows-os)
package/docs/DISCOVERY.md CHANGED
@@ -12,6 +12,7 @@ This page is written for maintainers, search engines, package indexes, and AI re
12
12
  - npm: https://www.npmjs.com/package/trace-to-skill
13
13
  - Latest release: https://github.com/grnbtqdbyx-create/trace-to-skill/releases/latest
14
14
  - Use cases: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/USE_CASES.md
15
+ - Codex Issue Radar demo: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_RADAR.md
15
16
  - Codex issue map: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_MAP.md
16
17
  - Scorecard: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/SCORECARD.md
17
18
  - OpenAI OSS strategy: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/OPENAI_OSS_STRATEGY.md
@@ -98,7 +99,8 @@ npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format
98
99
  npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
99
100
  npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
100
101
  npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
101
- npx trace-to-skill issue-map --repo openai/codex --limit 100 --output codex-issue-map.md
102
+ npx trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
103
+ npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --issue-map-limit 100
102
104
  npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
103
105
  npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
104
106
  npx trace-to-skill redact ./runs --output redacted-runs
@@ -130,6 +132,7 @@ npx trace-to-skill suggest ./runs --target agents-md
130
132
  - OpenAI/Codex issue-ready Markdown from `trace-to-skill codex-report`
131
133
  - Packaged zero-setup Codex issue-report demo from `trace-to-skill demo`
132
134
  - OpenAI OSS support/application brief from `trace-to-skill oss-brief`
135
+ - Live Codex Issue Radar demo in `docs/CODEX_ISSUE_RADAR.md`
133
136
  - Codex issue-cluster mapping in `docs/CODEX_ISSUE_MAP.md`
134
137
  - GitHub issue demand mining in `docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md`
135
138
  - GitHub Action outputs for doctor, AGENTS lint, GitHub context guard, benchmark, and scorecard modes
package/docs/OPENAI_OSS_BRIEF.md CHANGED
@@ -3,7 +3,7 @@
3
3
  | Field | Value |
4
4
  | --- | --- |
5
5
  | Repository | https://github.com/grnbtqdbyx-create/trace-to-skill |
6
- | Package | trace-to-skill@0.1.88 |
6
+ | Package | trace-to-skill@0.1.89 |
7
7
  | License | Apache-2.0 |
8
8
  | Codex readiness | ready (100/100) |
9
9
  | Benchmark | pass, 38 cases |
@@ -27,7 +27,7 @@ API credits would power optional maintainer workflows on top of the local determ
27
27
  ## Evidence
28
28
 
29
29
  - Public repository: https://github.com/grnbtqdbyx-create/trace-to-skill
30
- - One-command package: npx trace-to-skill@0.1.88
30
+ - One-command package: npx trace-to-skill@0.1.89
31
31
  - Open-source license: Apache-2.0
32
32
  - Codex readiness doctor: ready, 100/100, 0 failed checks.
33
33
  - Public fixture benchmark: pass, 38 cases.
package/docs/USE_CASES.md CHANGED
@@ -59,7 +59,7 @@ What it proves:
59
59
  Recommended CI surface:
60
60
 
61
61
  ```yaml
62
- - uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
62
+ - uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
63
63
  with:
64
64
  mode: all
65
65
  doctor-threshold: "85"
@@ -74,7 +74,7 @@ Recommended CI surface:
74
74
  Use this when you want to see what Codex users are actually complaining about on GitHub before choosing the next fixture, report template, or diagnostic helper.
75
75
 
76
76
  ```bash
77
- npx trace-to-skill issue-map --repo openai/codex --limit 100 --output codex-issue-map.md
77
+ npx trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
78
78
  npx trace-to-skill issue-map --repo openai/codex --format json
79
79
  npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --issue-map-limit 100
80
80
  gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
package/llms.txt CHANGED
@@ -65,6 +65,7 @@ failed agent run -> failure class -> evidence-backed AGENTS.md/SKILL.md suggesti
65
65
 
66
66
  - README: https://github.com/grnbtqdbyx-create/trace-to-skill#readme
67
67
  - Use cases: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/USE_CASES.md
68
+ - Codex Issue Radar demo: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_RADAR.md
68
69
  - Codex issue map: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/CODEX_ISSUE_MAP.md
69
70
  - Discovery summary: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/DISCOVERY.md
70
71
  - Demo output: https://github.com/grnbtqdbyx-create/trace-to-skill/blob/main/docs/DEMO.md
@@ -102,7 +103,8 @@ npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format
102
103
  npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
103
104
  npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
104
105
  npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
105
- npx trace-to-skill issue-map --repo openai/codex --limit 100 --output codex-issue-map.md
106
+ npx trace-to-skill issue-map --repo openai/codex --state all --limit 100 --output codex-issue-radar.md
107
+ npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --issue-map-limit 100
106
108
  npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
107
109
  npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
108
110
  npx trace-to-skill redact ./runs --output redacted-runs
@@ -122,7 +124,7 @@ npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --is
122
124
  ## GitHub Action
123
125
 
124
126
  ```yaml
125
- - uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
127
+ - uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
126
128
  with:
127
129
  mode: all
128
130
  doctor-threshold: "85"
@@ -135,7 +137,7 @@ npx trace-to-skill init --issue-map-repo openai/codex --issue-map-state all --is
135
137
  ## Weekly Codex Issue Radar
136
138
 
137
139
  ```yaml
138
- - uses: grnbtqdbyx-create/trace-to-skill@v0.1.88
140
+ - uses: grnbtqdbyx-create/trace-to-skill@v0.1.89
139
141
  with:
140
142
  mode: issue-map
141
143
  issue-map-repo: openai/codex
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "trace-to-skill",
3
- "version": "0.1.88",
3
+ "version": "0.1.89",
4
4
  "description": "Turn failed AI coding-agent runs into reusable AGENTS.md rules, SKILL.md files, and eval evidence.",
5
5
  "type": "module",
6
6
  "main": "dist/src/index.js",
@@ -21,6 +21,7 @@
21
21
  "docs/ADOPTION_GUIDE.md",
22
22
  "docs/AGENTS_LINT.md",
23
23
  "docs/BENCHMARK.md",
24
+ "docs/CODEX_ISSUE_RADAR.md",
24
25
  "docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md",
25
26
  "docs/CODEX_ISSUE_MAP.md",
26
27
  "docs/DEMO.md",