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 dork-labs/dorkos --skill managing-specsgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/dork-labs/dorkos/managing-specs)<a href="https://agentmods.dev/skills/dork-labs/dorkos/managing-specs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/managing-specs/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/dork-labs/dorkos/managing-specs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/managing-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01162 |
| Opus 5 | $0.00016 | $0.00581 |
| Sonnet 5 | $0.00006 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
managing-specs 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing the Spec Manifest
The spec manifest (specs/manifest.json) tracks every specification in the project. Never edit it by hand — always use the manifest-ops script.
Running the Script
node --experimental-strip-types --disable-warning=ExperimentalWarning .claude/scripts/spec-manifest-ops.ts <command> [args] [options]
Canonical Statuses
Only four statuses are valid:
| Status | Meaning |
|---|---|
ideation |
Spec has 01-ideation.md |
specified |
Spec has 02-specification.md |
implemented |
Spec has 04-implementation.md |
superseded |
Replaced by a newer spec |
Non-canonical aliases are normalized automatically: draft -> ideation, specification -> specified, completed -> implemented.
Status Progression
Statuses move forward only: ideation -> specified -> implemented -> superseded. The script rejects regressions unless --force is passed.
When to Update Status
- After writing
01-ideation.md-> set toideation - After writing
02-specification.md-> set tospecified - After all implementation tasks complete -> set to
implemented - When replaced by a newer spec -> set to
superseded
Commands
Update status
node --experimental-strip-types --disable-warning=ExperimentalWarning \
.claude/scripts/spec-manifest-ops.ts update-status <slug> <status>
Add a new spec
node --experimental-strip-types --disable-warning=ExperimentalWarning \
.claude/scripts/spec-manifest-ops.ts add <slug> "Title" --status=ideation
Options: --status=<s>, --project=<p>, --created=YYYY-MM-DD.
Other operations
| Command | Purpose |
|---|---|
get <slug> |
Print a spec entry as JSON |
list [--status=<s>] |
List specs, optionally filtered |
audit [--json] |
Audit manifest vs filesystem |
fix [--dry-run] |
Auto-fix all audit findings |
remove <slug> |
Remove a spec entry from the manifest (leaves files) |
archive <slug> |
Retire a spec: move to specs/archive/ and drop the entry |
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.
- 5d ago First seen · 116 lines · 32 tokens per session scan A ffef7362d734
managing-specs is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,162 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
workspace-prune-working
Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files.
workspace-realign
Reorganize and update .aiwg/ documentation to reflect current project reality.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.