# Coders Talk > Real coding-agent sessions: what worked, where agents failed and what the human did about it. - name: talk.coders/library - version: 1.0.0 - connection class: unknown (unknown) - trust: 66/100 flags: unreachable - quality: 84/100 (good) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/talk.coders%2Flibrary - tools: https://api.protogrid.dev/v1/servers/talk.coders%2Flibrary/tools **Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to. ## Connection (mcpServers) ```json { "mcpServers": { "library": { "type": "http", "url": "https://coders.talk/mcp" } } } ``` ## Trust - hygiene: 100 - liveness: 0 - freshness: 100 - provenance: 85 - drivers: +repository +dns-namespace +website -unreachable(6 failures) +updated-24d-ago - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 84/100 (good) ### protocol: 88 (weight 25) - pass `protocol.modern`: supports 2026-07-28 (server/discover) - pass `protocol.stateless`: answers without a session - pass `protocol.transport`: streamable HTTP - warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 86 (weight 30) - pass `tools.descriptions`: every tool has a description - pass `tools.description_length`: descriptions are concise - pass `tools.schemas`: every tool has an object input schema - pass `tools.annotations`: 10 of 10 tools declare readOnlyHint or destructiveHint - fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_task_context (idempotentHint, openWorldHint); get_session_excerpt (idempotentHint, openWorldHint); get_coding_agent_session (destructiveHint, idempotentHint, openWorldHint); … - pass `tools.token_cost`: about 2,056 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 75 (weight 15) - warn `stability.changes`: 13 tool changes in 30 days - pass `stability.rug_pull`: no tool changed its meaning under the same name ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 10, about 2,056 tokens to load them all - tool set hash: 6112deb3cefe05f1684b15be394e89ae - tools last changed: 2026-10-07T10:04:21.908Z - badge: [![protogrid quality](https://protogrid.dev/badge/talk.coders/library.svg)](https://protogrid.dev/servers/talk.coders/library) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-07 `attach_session_to_task` changed (description, inputSchema) - before: After the user chooses a task to continue, attach the actual current session to it. Use the client and session ID from the local plugin context, never guess IDs. This records a private link; it does not upload or publish history. - after: After the user chooses a task to continue, attach the actual current session to it. Use the client and session ID from the local plugin context, never guess IDs. Pass continues: the session_id (from get_task_context) of the session you are continuing, usually the latest one you read; your session then goes on in that session's draft, so one Build shows the work of both agents. This records a private link; it does not upload or publish history. - 2026-10-06 `attach_session_to_task` added - After the user chooses a task to continue, attach the actual current session to it. Use the client and session ID from the local plugin context, never guess IDs. This records a private link; it does not upload or publish history. - 2026-10-06 `get_session_excerpt` added - Read more turns from an accessible private work session. Use session_id returned by get_task_context and cursor to page through the source. - 2026-10-06 `get_task_context` added - Read private task context after selecting a task. Returns source excerpts without a paid summary call. Check the actual checkout before continuing. Fetch more session turns if excerpts are insufficient. - 2026-10-06 `search_my_work` added - Find your own or team tasks. For continuing work, get the current repository key from the local plugin at query time and search that project first. Offer every matching task newest first when there are multiple; never silently broaden a repository search. No model generation. - 2026-10-05 `list_team_tasks` added - Your team's pieces of work on Coders Talk, grouped from its members' agent sessions: title, task number, project, when it was last worked on, and its latest sessions (open one with get_coding_agent_session). Use when picking up work a teammate started, or to see what is going on in a project. Only for tokens of a team member. - 2026-10-05 `search_coding_agent_sessions` changed (inputSchema) - 2026-10-03 `find_coding_agent_failures` changed (inputSchema, outputSchema) - 2026-10-03 `get_coding_agent_session` changed (description, inputSchema, outputSchema) - before: Coders Talk library: read one published session found with search_coding_agent_sessions or find_coding_agent_failures. detail "brief" (default): the goal, the first prompt, the outcome and the numbers. detail "moments": every moment in order, with the prompts that worked, where the agent failed and why the human stepped in. - after: Coders Talk library: read one published session found with search_coding_agent_sessions or find_coding_agent_failures. detail "brief" (default): the goal, the first prompt, the outcome, the whole verdict and the numbers. detail "moments": every moment in order, with the prompts that worked, where the agent failed and why the human stepped in. - 2026-10-03 `search_coding_agent_sessions` changed (inputSchema, outputSchema) Full history: https://api.protogrid.dev/v1/servers/talk.coders%2Flibrary/changes ## Remotes - https://coders.talk/mcp (streamable-http, auth none, reachable false, uptime30d 0.85714287) ## Packages _none_ ## Tools (10) - `attach_session_to_task`: After the user chooses a task to continue, attach the actual current session to it. Use the client and session ID from the local plugin context, never guess IDs. Pass continues: the session_id (from get_task_context) of the session you are continuing, usually the latest one you read; your session then goes on in that session's draft, so one Build shows the work of both agents. This records a private link; it does not upload or publish history. - `find_coding_agent_failures`: Coders Talk library: find moments where coding agents failed on a similar problem and what the human did about it. Use after two or three failed attempts at the same problem. Query: the symptom or error message in a few words, without paths or secrets. - `finish_session_upload`: Coders Talk: step 2 of sending the current coding session, after the Coders Talk skill's upload step put it at the link from start_session_upload. Makes a private draft (or the team's, as the preview said) and returns its link. Nothing is published: the user reviews the draft on coders.talk. - `get_coding_agent_session`: Coders Talk library: read one published session found with search_coding_agent_sessions or find_coding_agent_failures. detail "brief" (default): the goal, the first prompt, the outcome, the whole verdict and the numbers. detail "moments": every moment in order, with the prompts that worked, where the agent failed and why the human stepped in. - `get_session_excerpt`: Read more turns from an accessible private work session. Use session_id returned by get_task_context and cursor to page through the source. - `get_task_context`: Read private task context after selecting a task. Returns source excerpts without a paid summary call. Check the actual checkout before continuing. Fetch more session turns if excerpts are insufficient. - `list_team_tasks`: Your team's pieces of work on Coders Talk, grouped from its members' agent sessions: title, task number, project, when it was last worked on, and its latest sessions (open one with get_coding_agent_session). Use when picking up work a teammate started, or to see what is going on in a project. Only for tokens of a team member. - `search_coding_agent_sessions`: Coders Talk library: find published sessions where developers did a similar task with a coding agent. Use before a non-trivial task on a known stack, or when the user asks how others did something; skip small edits and questions about this repository. Returns up to 5 cards with the outcome, how long it took and how often the human had to step in. Query: the task in a few words, e.g. "migrate queues to horizon". An empty result means nobody has published such a session yet. - `search_my_work`: Find your own or team tasks. For continuing work, get the current repository key from the local plugin at query time and search that project first. Offer every matching task newest first when there are multiple; never silently broaden a repository search. No model generation. - `start_session_upload`: Coders Talk: step 1 of sending the current coding session to the user's Coders Talk drafts, for the Coders Talk skill or plugin only. Call it only after the user asked to send this session and agreed to what the skill's preview showed. Returns a one-time upload link (15 minutes) for the skill's upload step, and an upload_id for finish_session_upload. Never put anything else at the link.