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 skills add joenandez/spectre --skill spectre-work-recordgit clone --depth 1 https://github.com/joenandez/spectreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joenandez/spectre/spectre-work-record)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-work-record"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-work-record/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-work-record"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-work-record.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00046 | $0.01110 |
| Opus 5.5 | $0.00018 | $0.00444 |
| Sonnet 5.5 | $0.00009 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
spectre-work-record scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-record
Purpose
Truthful work history; workflow state/telemetry own live progress. Capture never changes delivery, verification or acceptance authority.
Inputs
- Exact run/work identity and applicable branch, PR or repository/base/head/diff association; observed lifecycle, account, entry points, tag intent and prior revision.
- Owned boundary: one Execute start/completion; meaningful blocked handoff/resolution when authority, control or context prevents safe continuation/resumption; Ship after PR creation; standalone Create PR terminal write only without an Execute/Ship owner; explicit snapshot/correction, including outside workflows.
Working Set
- Reuse applicable discoveries/loads; refine only unresolved questions. Read
references/work-capture-input.jsonand${PLUGIN_ROOT}/skills/spectre-capture/references/tagging-policy.md. - Use acquired entry points; focus-read as needed: path, symbol/document section, observed positive line, role. Explain unavailable/non-code portions, including uncreated start locations; never invent locations or dump files.
Outputs + DONE
Short title/routing summary and required identity/provenance/status metadata, derived reliably. Complementary fields:
requestedOutcome: request;scope: boundaries.actualChanges: delivered behavior/artifacts;reasons: non-obvious rationale/trade-offs. Start/blocked accounts distinguish delivered from undelivered.discoveries: findings and maintained-authority links;relatedContext: typed entry points and bounded references.verification: observed checks;remainingWork: residual implementation. Structured verification and PR lifecycle remain authoritative.
State absence truthfully; omit filler, duplicated narrative/state. New/revised accounts stay under 2,000 estimated rendered tokens; reference evidence, not logs.
DONE: permitted boundary has a truthful account or surfaced skip/no-op/conflict/failure, with exact work ID, revision and canonical recordPath when applicable.
What ships with it
1 file 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.
- 16d ago Changed · +11 lines · -62 tokens per session 4c8d635f989c
- 29d ago Changed d0854b67e2c2
- 1mo ago First seen · 47 lines · 108 tokens per session scan A 4028698442c1
spectre-work-record is a skill published in the GitHub repository joenandez/spectre (165 stars, last pushed 15d ago), licensed MIT. It adds 46 tokens to every session and 1,110 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
rem-page-org
What an organisation's page in the notebook is made of — the fixed sections, when a company earns a page at all instead of staying a field on a person's, and the rules that keep it from becoming a second copy of everyone who works there. Composed into every stage that writes one.