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 ksprashu/agent-skill-forge --skill workgit clone --depth 1 https://github.com/ksprashu/agent-skill-forgeWrote 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/ksprashu/agent-skill-forge/work)<a href="https://agentmods.dev/skills/ksprashu/agent-skill-forge/work"><img src="https://agentmods.dev/badge/skills/ksprashu/agent-skill-forge/work/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/ksprashu/agent-skill-forge/work"><img src="https://agentmods.dev/badge/skills/ksprashu/agent-skill-forge/work.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 | $0.00051 | $0.08768 |
| Opus 5.5 | $0.00020 | $0.03507 |
| Sonnet 5.5 | $0.00010 | $0.01754 |
| Haiku 4.5 | $0.00005 | $0.00877 |
Grade A, and why
work 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 4d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
40 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.
- fixtures/designs/hollow_proposal.md 1.5 KB
- fixtures/designs/substantive_proposal.md 3.4 KB
- fixtures/focused_dag.md 2.2 KB
- fixtures/known_fake/README.md 1.2 KB
- fixtures/known_fake/src/evaluator.py 669 B runs code
- fixtures/known_fake/src/pipeline.py 401 B runs code
- fixtures/known_fake/tests/test_evaluator.py 863 B runs code
- fixtures/known_good/README.md 704 B
- fixtures/known_good/src/evaluator.py 3.0 KB runs code
- fixtures/known_good/src/pipeline.py 1.4 KB runs code
- fixtures/known_good/tests/test_evaluator.py 2.8 KB runs code
- fixtures/swarm_dag.md 2.8 KB
- references/adversarial_committee.md 6.1 KB
- references/competitive_branching.md 10.0 KB
- references/domain_autowiring.md 4.6 KB
- references/integrity_modes.md 3.4 KB
- references/orchestrator_protocol.md 17 KB
- references/sentinel_protocol.md 10 KB
- references/team_topologies.md 6.6 KB
- references/visual_production_guide.md 28 KB
- scripts/arbiter_eval.py 26 KB runs code
- scripts/autowire.py 20 KB runs code
- scripts/dag_validator.py 58 KB runs code
- scripts/forensic_audit.py 43 KB runs code
- scripts/gate_executor.py 51 KB runs code
- scripts/scaffold_work.py 44 KB runs code
- scripts/visual_engine/__init__.py 1.6 KB runs code
- scripts/visual_engine/c4_generator.py 9.2 KB runs code
- scripts/visual_engine/manifest.py 13 KB runs code
- scripts/visual_engine/sequence_generator.py 6.3 KB runs code
- scripts/visual_engine/what_if_compiler.py 24 KB runs code
- tests/test_adversarial_hardening.py 23 KB runs code
- tests/test_arbiter_eval.py 18 KB runs code
- tests/test_autowire.py 21 KB runs code
- tests/test_dag_validator.py 29 KB runs code
- tests/test_forensic_audit.py 27 KB runs code
- tests/test_gate_executor.py 55 KB runs code
- tests/test_lifecycle_swarm.py 11 KB runs code
- tests/test_visual_engine.py 30 KB runs code
- tests/test_visual_scaffold.py 19 KB runs code
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.
- 4d ago Changed 6bb0373fb301
- 6d ago Changed · +127 lines 685756acbde3
- 18d ago Changed · +6 lines · +18 tokens per session 172724b3d50d
- 27d ago Changed · +176 lines ded442e0f18c
- 28d ago First seen · 168 lines · 33 tokens per session scan A 4cf78724ad1c
work is a skill published in the GitHub repository ksprashu/agent-skill-forge (2 stars, last pushed 5d ago), with no licence file. It adds 51 tokens to every session and 8,768 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 2026-09-11.
Other skills, from other repositories
devhost-debug
Inspect this extension running in the Antigravity IDE Extension Development Host (F5) - sidebar DOM and screenshots, extension host state through non-pausing logpoints, the dev host's own Language Server and log, and Auto-Accept dry runs. Use after changing UI, webview messages, connection or parsing, or automation…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
execute
Execute an approved Maestro implementation plan using the shared session-state contract.
orchestrate
Run the full Maestro workflow for complex engineering tasks that need a mandatory design dialogue, approved implementation plan, and then execution with shared session state.
resume-session
Resume an interrupted Maestro session using the existing active-session file and shared phase tracking.
security-audit
Run a Maestro-style security assessment for authentication, authorization, data exposure, secret handling, and exploitability risks.