CodeTelemetry
Code Telemetry LLC v0.1.8
Explore your coding history
From the developer
Declared capabilities
- Read
Cost & access
This plugin reads coding-session history. It does not sell products or process payments.
Declared limitations
- Unrelated coding request: answer directly without CodeTelemetry tools.
- Unsupported mutation: explain read-only capabilities; do not claim deletion or execute a write.
- Unauthorized history: do not expose or claim access to any other tenant.
Onboarding example
Use CodeTelemetry to read my recent sessions in this repo and tell me how they went.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 17, 2026. Package observed Nov 17, 2026.
Description
From the marketplace listing
CodeTelemetry lets ChatGPT read your own Claude Code, Codex and Kiro session history: prompts, commands, tool outputs and exit codes, with links to recorded evidence. ChatGPT analyzes the events; saved interpretations, comparisons and planning guidance are optional hints to verify. Use it for questions about past sessions or a next task informed by that history. Private pilot: access requires an invited CodeTelemetry account.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 17, 2026. Last seen Nov 17, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Connect LeagueSaga to ask questions about your fantasy football league history. Explore championships, standings, records, matchups, draf...
Shared terms: history, explore, verify, question
-
Turn a rough repository idea into a decision-complete implementation: read the code first, then work the decision tree in rounds until no...
Shared terms: coding, verify, code, question
-
Ask questions about your BEXEL CDE project data.
Shared terms: explore, analyze, question
-
Ask questions about your BEXEL CDE project data.
Shared terms: explore, analyze, question
-
Uses the real vendored Impeccable workflow. Specialized for shaping UX and UI decisions and task structure before any interface code is w...
Shared terms: coding, task, code
Keywords
Files & skills
File archives
Skill instructions
plan-coding-session8.26 KB
---
name: plan-coding-session
description: Analyze the user's own past Claude Code, Codex and Kiro sessions in CodeTelemetry and plan the next one from them. Use when the user asks what happened in their sessions, what went wrong or well, how similar work went before, how to approach similar work using their session history, or its historical sizing. Do not use for general coding questions that do not involve their session history.
---
# Analyze past sessions and plan the next one
CodeTelemetry supplies recorded facts about the user's sessions. You do the
analysis:
- what the user wanted;
- what each operation actually did;
- whether checks ran and passed;
- what failed, what recovered and what stayed unresolved;
- what to do differently next time.
CodeTelemetry's own interpretations are optional hints to check, never the
answer.
## Workflow
Use only the tools the question needs; this is not a mandatory chain. Attaching CodeTelemetry alone does not justify a call for unrelated coding help. Use a known session id directly, without searching again. For raw-events-only analysis or comparison, skip the optional classification tools. Stop when the evidence answers the question.
1. **`search_sessions`**: find the relevant sessions. Filter by `repo` when
the user names a repository, and put topic words in `q`. Keep `limit` small
(5–10). Results are ordered by `lastSeen`: when a session was last active,
not when it started or finished.
- "My latest sessions" is literal: leave `activity` unset and list what
comes back.
- For recent coding work ("my last five real sessions", "what did I work
on"), pass `activity: "substantive"`. It keeps only sessions with observed
agent work, including brief, failed, and abandoned ones. `activityCounts`
says how many records it left out. `instrumentation_only` records showed
tool or connector traffic but no prompt, model call, or usage.
`insufficient_evidence` records lack the telemetry to tell either way.
Report those counts.
- Search covers a bounded recent window, and responses say `truncated`.
Fewer results than you asked for is a complete answer for that window.
2. **`read_session_events`**: read only the evidence needed for the question.
Read up to four independent sessions in parallel when the client supports it.
- **Brief summary or comparison.** Start with `direction: "backward",
limit: 6` for each relevant session. These are ending events, not a
complete audit. Add a small opening page (`position: 0, limit: 2`) only
when the original request is needed. Prefer targeted command reads over
paging through the intervening history. Stop once the evidence supports
the requested answer; disclose unread positions and coverage gaps.
- **Full audit.** Start at the first page and continue as needed. A brief
comparison does not require a full audit of every session.
- **More pages.** Continue with `nextCursor`. Use `direction: "backward"`
to read how the session ended.
- **Problems.** Pass `outcome: "failed"` to list recorded failures, then
`around` with an event's `position` to see what came before and after it.
- **Commands.** Pass `text` (for example "npm test") or `tool` to find
commands. These filters match words, not meaning.
- **Full text.** `expand` returns an event's full retained text. If it
returns a `continuation`, pass that back to read the rest.
3. **Judge each operation yourself**, from its recorded command and output:
- **Reading is not verification.** A command that only prints files (`cat`,
`sed -n`, `head`, a grep over sources) did not check anything, even when
the file is a test.
- **Exit 0 is not a pass.** A wrapper can exit 0 without running its check.
Output such as "no node_modules; skipping tsc" means the typecheck did not
run.
- **No match is a result.** A search that finds nothing exits 1 (`grep`,
`rg`); that isPreview of the first 4,000 characters. Read full instructions →
Release notes
Privacy-policy revision after review feedback: explicit five-tool data categories and ChatGPT transfers, verified recipients and store-specific retention, manual export/deletion and backup exceptions, aligned setup/security docs, and optional marketing analytics controls. Read-only tools, personal access, OAuth scope and reviewer examples are unchanged.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- Code Telemetry LLC
- Keywords
- See keywords
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Read
Package observed Nov 17, 2026.
Technical details
- First seen
- Nov 17, 2026 · 00:00 UTC
- Last seen
- Nov 17, 2026 · 06:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ae4a8f49bd08191ace195653be2ef6e
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.