Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bks-lab/open-bridge/task-close-postmortemnpx skills add bks-lab/open-bridge --skill task-close-postmortemgit clone --depth 1 https://github.com/bks-lab/open-bridgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00168 | $0.02477 |
| Opus 5 | $0.00084 | $0.01239 |
| Sonnet 5 | $0.00034 | $0.00495 |
| Haiku 4.5 | $0.00017 | $0.00248 |
Grade A, and why
task-close-postmortem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task-Close Postmortem
Captures a short reflection at task close, maps any surfaced gaps to concrete Bridge-File-Improvement-Proposals, and writes both back as structured artifacts.
The skill is always optional and always interruptible — every question is
skippable, and skipping all six leaves the task unchanged from today's behavior.
Default-on (per bridge-config.yaml.learning.postmortem.enabled) but cost-light:
fast-path through all six skips is <20 seconds.
When this skill runs
- Auto, via
task-sync.mdPhase 3b — every time a task closes, after the dual_doku self-check passes and before the 3-step move. - Manual — when the user says any of: "/postmortem the last hour", "reflect on the piece just finished", "post-mortem this", "what did we learn from X". In manual mode the scope is not bound to a task folder — the skill reflects on the recent activity (last log.md entries, recent commits, recent file edits). No frontmatter writes happen in manual mode; output is only the proposals.
Inputs
Auto mode:
work/tasks/<slug>/STATUS.md— the task being closedworkflow/contexts/<context>.yamlif STATUS references a context- recent entries from
work/log.md(last 24h or all entries since taskcreated)
Manual mode:
- last N log.md entries (N defaults to last 10, or "the last hour")
- recent uncommitted git diff in this Bridge repo and any other repos touched
The six questions
(Full script in references/postmortem-questions.md.)
Surface them one at a time. Accept skip-phrases from
bridge-config.yaml.learning.postmortem.skip_phrases — default
["skip", "next", "—", "no", "next", "."]. If
cutdown_after_skips (default 3) consecutive skips occur, switch
to Cutdown mode for the remaining questions: ask only the single
catch-all "anything else worth noting?". Empty answer → done.
| # | Question (EN) | Writes to |
|---|---|---|
| 1 | Time invested? | frontmatter time_invested |
| 2 | Estimate vs actual? | frontmatter estimate_vs_actual |
| 3 | What went well? | body ## Postmortem → "What went well" |
| 4 | What burned time? | body ## Postmortem → "What did not go well" |
| 5 | Did the bridge fail you? | frontmatter bridge_gaps[] + body |
| 6 | Concrete improvement? | proposal file + body |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 212 lines · 168 tokens per session scan A 3f5da87a0329
task-close-postmortem is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 2d ago), licensed MIT. It adds 168 tokens to every session and 2,477 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4)…
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
retrospect-external-babysitter-run
For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/ /) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but…